Information processing method and device

Abstract

An embodiment of the present application provides an information processing method and apparatus. After obtaining a list of candidate users to be processed from multiple source channels, the method first filters non-target push users among N candidate push users based on a preset filtering rule engine to obtain P target push users. Then, based on the target reference information of the target push users, the method determines the target push services and designated agent terminals assigned to the target push users. Then, based on the target push services and designated agent terminals corresponding to the P target push users, a list of users to be pushed is generated. Each designated agent terminal can push services to its assigned target push users in a targeted manner. This not only improves the pertinence and accuracy of service push, thereby enhancing the user's answering experience, but also avoids the problem of wasting agent resources due to targeting users whose risk levels are greater than a preset threshold as target push users, thereby improving agent utilization.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent outbound call centers, and in particular to an information processing method and device. Background Art

[0002] The rapid development of intelligent outbound call centers has significantly reduced communication costs between customer service personnel (i.e., agents) and customers (i.e., target users). In intelligent outbound call systems, agents are randomly assigned a list of outbound users. Agents then use their own caller lists to push services to target users via their terminals. However, in existing technologies, not only are outbound call lists randomly assigned, but agents often randomly push services to target users based on their own experience. This inevitably results in poor targeting and accuracy of service push. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide an information processing method and device, which can not only improve the pertinence and accuracy of service push, thereby improving the user's answering experience, but also avoid the problem of wasting agent resources due to targeting users with risk levels greater than a preset threshold as push users, thereby improving the utilization rate of agent personnel.

[0004] In order to implement the above technical solution, the embodiment of the present application is implemented as follows:

[0005] In a first aspect, an embodiment of the present application provides an information processing method, the method comprising:

[0006] Obtain a list of candidate users to be processed; the list of candidate users includes N candidate push users from multiple source channels, where N is an integer greater than 1;

[0007] Filtering non-target push users from the N candidate push users based on a preset filtering rule engine to obtain P target push users; P is an integer greater than 1 and less than N;

[0008] Determine the target push service and designated agent terminal assigned to the target push user based on the target reference information of each target push user; the target reference information includes the source channel identifier of the target push user;

[0009] Based on the target push service and designated agent terminal corresponding to each target push user, a list of users to be pushed is generated; the list of users to be pushed includes a sub-list of outbound users of each agent terminal.

[0010] In a second aspect, an embodiment of the present application provides an information processing device, the device comprising:

[0011] A list acquisition module is used to obtain a list of candidate users to be processed; the candidate user list includes N candidate push users from multiple source channels, where N is an integer greater than 1;

[0012] A first determining module is configured to filter non-target push users from the N candidate push users based on a preset filtering rule engine to obtain P target push users; P is an integer greater than 1 and less than N;

[0013] A second determining module is configured to determine the target push service and designated agent terminal assigned to the target push user based on the target reference information of each target push user; the target reference information includes a source channel identifier of the target push user;

[0014] The list generation module is used to generate a list of users to be pushed based on the target push service and designated agent terminal corresponding to each target push user; the list of users to be pushed includes an outbound user sub-list of each agent terminal.

[0015] In a third aspect, an embodiment of the present application provides an information processing device, the device comprising:

[0016] A processor; and a memory arranged to store computer executable instructions, the executable instructions being configured to be executed by the processor, the executable instructions comprising instructions for executing the steps in the method as described in the first aspect.

[0017] In a fourth aspect, an embodiment of the present application provides a storage medium, wherein the storage medium is used to store computer-executable instructions, and the executable instructions enable a computer to execute the steps in the method described in the first aspect.

[0018] It can be seen that in the embodiment of the present application, after obtaining a list of candidate users to be processed from multiple source channels, the non-target push users among the N candidate push users are first filtered based on a preset filtering rule engine to obtain P target push users, and then the target push services and designated agent terminals assigned to the target push users are determined based on the target reference information of the target push users; then, a list of users to be pushed is generated based on the target push services and designated agent terminals corresponding to the P target push users, so that each designated agent terminal can push services to the target push users assigned to them in a targeted manner; that is, in the process of determining the list of users to be pushed, the candidate user list is first filtered for non-target push users, and then the target push users selected by the risk filtering are assigned target push services and designated agent terminals. This not only improves the pertinence and accuracy of service push, thereby improving the user answering experience, but also avoids the problem of wasting agent resources due to using users whose risk levels are greater than a preset threshold as target push users, thereby improving the utilization rate of agent personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in one or more of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 A schematic diagram of an application scenario of the information processing system provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of a first flow chart of the information processing method provided in an embodiment of the present application;

[0022] Figure 3 A second flow chart of the information processing method provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the first implementation principle of the information processing method provided in the embodiment of the present application;

[0024] Figure 5 A schematic diagram of a second implementation principle of the information processing method provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of the module composition of the information processing device provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of the structure of the information processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the technical solutions in one or more of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of one or more embodiments of the present application, rather than all embodiments. Based on one or more embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0028] It should be noted that, in the absence of conflict, one or more embodiments and features in the embodiments of the present application may be combined with each other. The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] One or more embodiments of the present application provide an information processing method and device, taking into account that each candidate push user in the candidate user list is directly used as a target push user. If there is a user with a risk level greater than a preset threshold in the candidate user list, there will inevitably be a problem of wasting agent resources. Considering that the actual needs of candidate push users from multiple source channels may be different, if the agent manually selects the service to be pushed to the target push user based on experience, there will inevitably be a problem of low accuracy of service push due to human factors. Considering that if the target push user is randomly assigned to the agent, there will inevitably be a situation where the user answering experience is poor due to the mismatch between the agent service capability and the user's importance level, and even the loss of important users may occur. Based on the above problems, the present technical solution, after obtaining the candidate user list to be processed from multiple source channels, first selects the target user based on preset filtering rules. The engine filters non-target push users from N candidate push users to obtain P target push users, and then determines the target push services and designated agent terminals assigned to the target push users based on the target reference information of the target push users; then, a list of users to be pushed is generated based on the target push services and designated agent terminals corresponding to the P target push users, so that each designated agent terminal can push services to its assigned target push users in a targeted manner; that is, in the process of determining the list of users to be pushed, the candidate user list is first filtered for non-target push users, and then the target push users selected by the risk filtering are assigned target push services and designated agent terminals. This not only improves the pertinence and accuracy of service push, thereby improving the user answering experience, but also avoids the problem of wasting agent resources due to targeting users whose risk levels are greater than a preset threshold as push users, thereby improving the utilization rate of agent personnel.

[0030] Figure 1 This is a schematic diagram of an application scenario of the information processing system provided in the embodiment of the present application, such as Figure 1 As shown, the system includes: a backend server, an agent terminal, and a client. The client can be a mobile terminal such as a smartphone or a tablet computer, or a terminal device such as a personal computer. The backend server can be an independent server or a server cluster composed of multiple servers. The agent terminal can be a terminal device used by customer service personnel when interacting with target push users. The specific process of the above information processing is as follows:

[0031] After obtaining the list of candidate users to be processed, if the list includes N candidate push users from multiple source channels, the backend server filters non-target push users from the N candidate push users based on the preset filtering rule engine to obtain P target push users; where N is an integer greater than 1 and P is an integer greater than 1 and less than N;

[0032] The backend server determines the target push service and designated agent terminal assigned to the target push user based on the target reference information of each target push user; wherein the target reference information includes the source channel identifier of the target push user;

[0033] The backend server generates a list of users to be pushed based on the target push service and designated agent terminal corresponding to each target push user; the list of users to be pushed includes a sublist of outbound users of each agent terminal;

[0034] The agent terminal receives the outbound user sublist sent by the background server, and makes outbound calls to the clients assigned to the respective target push users based on the outbound user sublist, so that the agent can push the target push service to the target candidate users.

[0035] Specifically, Figure 2 A first flow chart of an information processing method provided in one or more embodiments of the present application is provided. Figure 2 The method in can be Figure 1 The background server in the execution, such as Figure 2 As shown, the method at least includes the following steps S202 to S208:

[0036] S202, obtaining a list of candidate users to be processed; wherein the list of candidate users includes N candidate push users from multiple source channels, where N is an integer greater than 1;

[0037] Specifically, for the application scenario of the outbound call push service, a candidate user list is first obtained based on multiple user source channels. The candidate user list may include basic information records corresponding to N candidate push users, each of which includes multiple information fields. For example, the push information record corresponding to candidate push user a may include user identifier a (such as a mobile phone number or device number), source channel identifier x, and at least one information field of user attribute information;

[0038] In the specific implementation, for the process of obtaining the candidate user list, as long as it is detected that a user has triggered any preset access scenario, the user will be used as a candidate push user to form a candidate user list containing N candidate push users; wherein, each preset access scenario is used as a user source channel (that is, each user source channel corresponds to a preset access entrance). For example, the user downloaded a preset application (such as an application that provides loan services or an online shopping application), which corresponds to the source channel identifier x1; for another example, the user accessed a preset information item (such as a displayed advertising link) on an associated application of the preset application (such as a payment application, an information application), which corresponds to the source channel identifier x2; for another example, the user searched for a specified keyword on a preset search engine, etc., which corresponds to the source channel identifier x3; then the candidate push users from multiple user source channels are summarized to obtain a list of candidate users to be processed.

[0039] S204, filtering non-target push users from the N candidate push users based on a preset filtering rule engine to obtain P target push users; where P is an integer greater than 1 and less than N;

[0040] Among them, the above-mentioned preset filtering rule engine can be an engine that includes a preset filtering rule set, which is used to automatically identify whether the candidate push user is a non-target push user with a risk level greater than a preset threshold based on the preset filtering rule set and the attribute information of the candidate push user; wherein, the preset filtering rules may include at least one of the following: the business application being rejected within a certain historical time period, the user's registered account being cancelled, the age being outside the preset range, and the available credit limit being less than the preset threshold. It can be set according to actual business needs and does not affect the protection scope of this application.

[0041] Specifically, after obtaining the candidate user list, risk filtering is performed on the N candidate push users in the candidate user list, and M non-target push users whose risk levels are greater than a preset threshold are filtered out to screen out P target push users, where M is an integer greater than 0 and less than N. In specific implementation, the candidate push users other than the M non-target push users in the candidate user list can be directly used as P target push users, that is, the sum of M and P is equal to N, or the candidate push users other than the M non-target push users in the candidate user list can be filtered twice to obtain P target push users, that is, the sum of M and P is less than N.

[0042] Among them, in order to further improve the accuracy of the P target push users finally determined, the candidate push users other than the M non-target push users in the candidate user list can be filtered twice to obtain the P target push users finally determined. Specifically, in S204, based on the preset filtering rule engine, the non-target push users in the above N candidate push users are filtered to obtain P target push users, which specifically includes: first, based on the preset filtering rule engine, filtering the M non-target push users in the above N candidate push users; then, based on the user attribute information of the candidate push users and the preset catch-all rule, performing a catch-all filter on the (NM) candidate push users to determine the P target push users among the (NM) candidate push users; that is, for the (NM) candidate push users other than the M non-target push users, a catch-all rule filtering is performed based on the user attribute information of the candidate push users. If the catch-all filtering result is If the user attribute information matches at least one fallback rule, the candidate push user is determined as a non-target push user; if the fallback filtering result is that the user attribute information does not match any fallback rule, the candidate push user is determined as a target push user; that is, for the remaining (NM) candidate push users screened by the preset filtering rule engine, the (NM) candidate push users are not directly determined as P target push users, but the (NM) candidate push users are filtered a second time based on the fallback rules, and only the candidate push users that pass the fallback rules are used as target push users, which can further filter out non-target push users who do not meet the preset requirements among the (NM) candidate push users; among them, the fallback rules may include age restriction rules, credit restriction rules, available credit limit rules, etc., which can be set according to actual business needs and do not affect the protection scope of this application.

[0043] In addition, during the specific implementation, the key push users among the N candidate push users can be determined based on the user identification of the candidate push users, where the key push users can include at least one of the existing users whose number of successful business pushes is greater than a preset threshold and the users whose credit is greater than a preset threshold. The key push users are directly determined as the target push users, that is, there is no need to perform the risk filtering process using the preset filtering rule engine for the key push users, but only the risk filtering process using the preset filtering rule engine is required for the non-key push users, that is, based on the preset filtering rule engine, the non-target push users among the non-key push users among the above-mentioned N candidate push users are filtered to obtain P target push users, which can improve the screening efficiency of the target push users.

[0044] S206, based on the target reference information of each target push user, determining the target push service and designated agent terminal assigned to the target push user; the target reference information includes the source channel identifier of the target push user;

[0045] Specifically, after screening and obtaining P target push users in the candidate user list, the P target push users are not directly and randomly assigned to X agents. Instead, the target push users are first assigned target push services and designated agent terminals that match them based on their target reference information. In specific implementation, the target push services corresponding to each target push user can be determined based on a pre-stored first correspondence, and the first correspondence includes a correspondence between a source channel identifier and an identifier of a service to be pushed, that is, a one-to-one correspondence between a target push service and a source channel identifier of a target push user. The target push service corresponding to the target push user can also be comprehensively determined based on the source channel identifier and other reference information of the target push user, that is, the target push service determination process is not only related to the source channel identifier of the target push user, but also to other reference information of the target push user (such as historical behavior data). This can further improve the accuracy of determining the target push service.

[0046] S208 : Generate a list of users to be pushed based on the target push service and designated agent terminal corresponding to each target push user; wherein the list of users to be pushed includes a sub-list of outbound users of each agent terminal.

[0047] Specifically, after determining the target push service and designated agent terminal for each target push user, a list of users to be pushed can be obtained. The list of users to be pushed can include push information records corresponding to Y target push users, where Y is equal to P or Y is less than P. Each push information record includes multiple information fields. For example, the push information record corresponding to target push user b may include user identifier b, service identifier i of the target push service, agent identifier j of the designated agent terminal, and at least one information field of user attribute information.

[0048] Next, the outbound user sub-list assigned to each designated agent terminal can be sent to the corresponding agent terminal. In this way, after receiving the outbound user sub-list, the agent terminal can make an outbound call to the client assigned to the respective target push user based on the outbound user sub-list through the intelligent outbound call system, so that the agent can push the target push service to the target candidate user.

[0049] In a specific implementation, in order to improve the risk filtering accuracy of the preset filtering rule engine, after filtering the non-target push users among the above-mentioned N candidate push users based on the preset filtering rule engine, it also includes: updating the filtering rule set in the filtering rule engine based on the user identifiers of the M non-target push users filtered out this time. For example, if the filtering rule set includes a list of banned users, the user identifier of the non-target push user is added to the banned user list of the filtering rule engine. In this way, when the candidate user list obtained next time is filtered based on the preset filtering rule engine, the non-target push user can be automatically and quickly filtered out based on the user identifier, that is, the filtering rule set in the filtering rule engine is continuously updated based on the risk filtering results of the candidate user lists obtained successively, thereby improving the filtering accuracy and filtering efficiency of the filtering rule engine.

[0050] In an embodiment of the present application, after obtaining a list of candidate users to be processed from multiple source channels, non-target push users among N candidate push users are first filtered based on a preset filtering rule engine to obtain P target push users, and then based on the target reference information of the target push users, the target push services and designated agent terminals assigned to the target push users are determined; then, based on the target push services and designated agent terminals corresponding to the P target push users, a list of users to be pushed is generated, so that each designated agent terminal can push services to its assigned target push users in a targeted manner; that is, in the process of determining the list of users to be pushed, the candidate user list is first filtered for non-target push users, and then the target push users selected by the risk filtering are assigned target push services and designated agent terminals. This not only improves the pertinence and accuracy of service push, thereby improving the user answering experience, but also avoids the problem of wasting agent resources due to targeting users whose risk levels are greater than a preset threshold as target push users, thereby improving the utilization rate of agent personnel.

[0051] Furthermore, considering that the same candidate push user may be included in different candidate user lists obtained successively, in order to avoid repeatedly calling the same user as an outbound call target within a short period of time, thereby preventing the same user from repeatedly receiving agent push calls within a short period of time, thereby further improving the user's answering experience, based on this, the above S208 generates a list of users to be pushed based on the target push service and the designated agent terminal corresponding to each target push user, specifically including:

[0052] Step A1: Generate an initial push user list based on the target push service and designated agent terminal corresponding to each target push user; wherein the initial push user list includes push information records corresponding to P target push users respectively;

[0053] Step A2: Generate a list of users to be pushed based on the initial push user list and the historical push user list; wherein the historical push user list includes multiple historical push users determined based on the candidate user list obtained within a preset historical time period, and the list of users to be pushed does not include the target push users included in the historical push user list.

[0054] Specifically, after determining the target push service and designated agent terminal for each target push user, a user list containing push information records corresponding to each of the P target push users can be directly determined as the list of users to be pushed. However, considering that the same candidate push user may be included in different candidate user lists obtained successively, it is determined for each target push user whether the target push user is included in the historical push user list. If so, it indicates that the target push user has already been determined as a historical push user. Therefore, to prevent the same user from repeatedly receiving agent push calls within a short period of time, target push users with the same user ID in both the initial push user list and the historical push user list need to be deleted, so that the final list of users to be pushed does not include the target push user included in the historical push user list. If the initial push user list and the historical push user list contain the target push user with the same user ID, the number of push information records included in the final list of users to be pushed is less than P, i.e., Y is less than P. If the initial push user list and the historical push user list do not contain the target push user with the same user ID, the number of push information records included in the final list of users to be pushed is equal to P, i.e., Y is equal to P.

[0055] That is, if the same user in the obtained initial candidate user list corresponds to at least two push information records (i.e., a candidate push user triggered at least two preset access entries within the time period when the current candidate user list to be processed was generated), the current candidate user list to be processed can first be merged with the same user record, that is, multiple push information records of the same candidate push user are merged to obtain the current candidate user list to be processed; however, considering that new candidate user lists are continuously obtained at preset time intervals, the same candidate push user may be included in different candidate user lists (i.e., a candidate push user triggered different preset access entries in different time periods when different candidate user lists were generated, that is, the time nodes when the candidate push user triggered the preset access entries are in different time periods). Therefore, in order to avoid repeatedly calling the same user in a short period of time, it is necessary to determine whether the initial push user list and the historical push user list contain target push users with the same user identifier, that is, whether a user has been included in the historical push user list within a short period of time, and then delete the target push users with the same user identifier in the initial push user list and the historical push user list to obtain the list of users to be pushed.

[0056] Furthermore, considering that the source channels of the same user in different candidate user lists may be different, the target push services corresponding to the same target push user (i.e., repeated push user) in the initial push user list and the historical push user list may also be different, which means that the target push user may be interested in any target push service or may be interested in multiple target push services at the same time. Considering that the current processing status of the outbound push task corresponding to the repeated push user in the historical push user list may be unfinished or completed, in the case where the outbound push task of the repeated push user is unfinished, the target push service corresponding to the repeated push user in the initial push user list may be added to the historical push user list, so that during the execution of the outbound push task corresponding to the repeated push user in the historical push user list, the agent can simultaneously push services to the target push user based on multiple target push services corresponding to the repeated push user. Based on this, after generating the list of users to be pushed based on the initial push user list and the historical push user list in the above step A2, the following step is also included:

[0057] Step A3: determining the current processing status of the outbound push tasks corresponding to the repeated push users in the initial push user list and the historical push user list;

[0058] Specifically, determine the target push users (i.e., repeated push users) who belong to both the initial push user list and the historical push user list, and then determine the current processing status of the corresponding outbound push task of the repeated push user in the historical push user list; that is, for a certain user, a target push service has been determined and assigned to a certain agent at a certain historical time node, and corresponds to a push information record in the historical push user list. Therefore, if multiple outbound user sub-lists in the historical push user list have been sent to the corresponding agent terminal, then the agent terminal will generate a corresponding outbound push task, but the current processing status of the outbound push task can be incomplete or completed.

[0059] Step A4: If the current processing status of the outbound push task corresponding to the repeatedly pushed user in the historical push user list is incomplete, determining whether the first push service and the second push service of the repeatedly pushed user are the same; wherein the first push service includes the target push service of the repeatedly pushed user in the initial push user list, and the second push service includes the target push service of the repeatedly pushed user in the historical push user list;

[0060] Step A5: If the first push service is different from the second push service, then based on the first push service, the target push service of the repeated push user in the historical push user list is updated.

[0061] For example, a user triggered the preset access entrances corresponding to different user source channels in a historical time period corresponding to the historical push user list and the information collection time period corresponding to the current candidate user list to be processed. For example, user A downloaded the preset application in a historical time period corresponding to the historical push user list, and clicked the advertising link on Alipay in the information collection time period corresponding to the current candidate user list to be processed. Therefore, user A is included in the candidate user lists obtained successively. Due to the different source channel identifiers, the automatically matched target push services may also be different (such as target push service 1 and target push service 2). Therefore, in order to avoid repeated calls to user A and ensure the accuracy of service push, target push service 2 is added to the push service set of user A in the historical push user list (that is, the push service set corresponding to user A includes target push service 1 and target push service 2).

[0062] Specifically, for each repeated push user, if the target push service of the repeated push user in the initial push user list is the same as any target push service of the repeated push user in the historical push user list, then only the push information record corresponding to the repeated push user in the initial push user list needs to be deleted; if the target push service of the repeated push user in the initial push user list is different from or the same as all the target push services of the repeated push user in the historical push user list, then not only the push information record corresponding to the repeated push user in the initial push user list needs to be deleted, but also the target push service corresponding to the repeated push user in the initial push user list needs to be added to the historical push user list, that is, for the same user, the newly determined target push service is added to the push service set of the user, so that when the agent calls the user, the newly determined target push service and the historically determined target push service are pushed to the user together. This can not only ensure the accuracy of service push, but also avoid different agents making repeated calls to the same user in a short period of time.

[0063] In specific implementation, Figure 3 As shown in FIG, a schematic diagram of a specific implementation principle of the above information processing method is given, which mainly includes:

[0064] Obtain a list of candidate users to be processed; wherein the list of candidate users includes N candidate push users from multiple source channels, where N is an integer greater than 1;

[0065] Based on a preset filtering rule engine, M non-target push users among the N candidate push users are filtered to obtain P target push users; where P is an integer greater than 1 and less than N;

[0066] Based on the target reference information of each target push user, determining the target push service and designated agent terminal assigned to the target push user; the target reference information includes the source channel identifier of the target push user;

[0067] Based on the target push services and designated agent terminals corresponding to each target push user, an initial push user list is generated; wherein the initial push user list includes push information records corresponding to P target push users respectively;

[0068] Delete target push users with the same user identifiers as those in the initial push user list and the historical push user list (i.e., repeated push users), to obtain a list of users to be pushed; wherein the list of users to be pushed includes push information records corresponding to Y target push users, i.e., the number of push information records included in the list of users to be pushed, Y, is less than P; and, if the current processing status of the outbound push task corresponding to the repeated push user in the historical push user list is incomplete, then update the target push service for the outbound push task corresponding to the repeated push user based on the first push service and the second push service of the repeated push user;

[0069] The outbound user sublist of each designated agent terminal in the above-mentioned user list to be pushed is sent to the corresponding agent terminal.

[0070] Furthermore, in order to be able to perform subsequent information processing operations based on the processing status of the outbound call push tasks corresponding to each target push user (for example, determining whether to update the target push service of the repeatedly pushed user based on the task processing status, or determining whether to add the target push user to the call ban list based on the target push user's acceptance of the service push event, etc.), therefore, in the above S208, after generating the list of users to be pushed based on the target push service corresponding to each target push user and the designated agent terminal, the following further operations are further included:

[0071] Step A6: Send the outbound user sublist to the corresponding agent terminal; wherein the outbound user sublist is used to instruct the agent terminal to generate an outbound push task corresponding to each target push user, and display the outbound push tasks corresponding to the target push users for which the agent terminal is responsible on a visual interface;

[0072] Step A7: receiving task processing feedback information sent by the agent terminal for the processed outbound call push task, and performing corresponding information processing operations based on the received task processing feedback information.

[0073] Specifically, the list of users to be pushed can be directly sent to the agent terminals of X agents. The agent terminals determine the outbound user sub-lists assigned to each of them in the list of users to be pushed based on the agent identifier j in the list of users to be pushed. Alternatively, the server can determine the outbound user sub-lists corresponding to each of the X agents based on the agent identifier j in the list of users to be pushed, and then send the corresponding outbound user sub-lists to the agent terminals of the X agents. Then, based on the multiple push information records in the received outbound user sub-list, the agent terminal generates outbound push tasks corresponding to the target push users assigned to it, and displays the multiple outbound push tasks corresponding to the outbound user sub-list on a visual interface. The agent enters corresponding task processing feedback information for a certain outbound push task on the visual interface. After detecting the agent's input operation for the certain outbound push task, the agent terminal sends the task processing feedback information corresponding to the input operation to the server. Then, the server performs corresponding information processing operations based on the task processing feedback information of the outbound push tasks corresponding to each target push user.

[0074] Specifically, the task processing feedback information may include feedback information indicating whether the outbound call push task for the first target push user has been completed, feedback information indicating whether there are any abnormalities in the service push process to the target push user (e.g., feedback information indicating the target push user's acceptance of the target push service), and feedback information from other dimensions. Based on this, the corresponding information processing operations are performed based on the received task processing feedback information in step A7, specifically including:

[0075] (1) If the task processing feedback information includes first feedback information indicating that the outbound call push task for the first target push user has been completed, then updating the processing status of the outbound call push task for the first target push user based on the first feedback information;

[0076] Specifically, the agent performs a first input operation on the visual interface for the first control corresponding to a certain outbound call push task (such as a click operation on the first control or a selection operation on any option in the drop-down options of the first control). After the agent terminal detects the first input operation of the agent, if the task processing feedback information corresponding to the first input operation is the first feedback information, the first feedback information is sent to the server. Then, the server updates the processing status of the outbound call push task of the first target push user based on the first feedback information of the outbound call push task corresponding to each target push user; for example, each push information record in the list of users to be pushed contains multiple information fields including any Based on the first feedback information, the task processing status field of the push information record corresponding to the first target push user is updated. In this way, the processing status of the outbound push task corresponding to each target push user can be accurately determined based on the first feedback information returned by the agent terminal, so that the corresponding information processing operation is performed based on the current processing status of the outbound push task. For example, based on the current processing status of the outbound push task, it is determined whether the target push service of the repeated push user needs to be updated; for another example, based on the current processing status of the outbound push task, the task processing completion status of the agent is determined, and then it is identified whether a certain agent needs to be assigned a task, etc.

[0077] (2) If the task processing feedback information includes second feedback information representing the target push user's acceptance level of the target push service, then based on the second feedback information, determine a second target push user whose acceptance level of the outbound push task is less than a preset threshold; and based on the user identification information of the second target push user, update the filtering rule set in the preset filtering rule engine.

[0078] Specifically, the agent performs a second input operation on the visual interface for the second control corresponding to a certain outbound call push task (such as a click operation on the second control or a selection operation on any option in the drop-down options of the second control). After detecting the second input operation of the agent, the agent terminal determines the second feedback information corresponding to the second input operation, and then sends the second feedback information to the server. Then, based on the second feedback information, the server determines the second target push user whose acceptance degree of the outbound call push task is less than a preset threshold, and updates the filtering rule set in the preset filtering rule engine based on the user identification information of the second target push user; and / or updates the outbound call push task of the target push user based on the second feedback information of the outbound call push task corresponding to each target push user. Task processing details information of the task; for example, if the multiple information fields contained in each push information record in the list of users to be pushed include a task processing details field, then based on the second feedback information, the task processing details field of the push information record corresponding to the target push user is updated; in this way, based on the second feedback information returned by the agent terminal, the acceptance degree of each target push user to the outbound push task can be accurately determined, and then the corresponding information processing operation can be performed based on the task processing details information corresponding to the target push user. For example, based on the task processing details information corresponding to the target push user, it is determined whether to add its user identification information to the banned user list of the filtering rule engine; for example, based on the task processing details information corresponding to the target push user, it is determined whether to use it as a key return visit user, etc.

[0079] like Figure 4 As shown, for example, after the agent has made a call to the target push user corresponding to a certain outbound call push task, he / she checks the first control indicating whether the task is completed. In this way, even if the outbound call push task has been assigned to the designated agent terminal, it is possible to promptly distinguish which outbound call push tasks have been processed and which have not been processed. For another example, after the agent has made a call to the target push user corresponding to a certain outbound call push task, he / she selects the target option corresponding to the user's acceptance level from the multiple drop-down options in the second control. In this way, it is possible to more intuitively and quickly determine the target push user's acceptance level for the outbound call push task.

[0080] Furthermore, considering that there may be irregular behavior of agents in not pushing services in accordance with the target push services assigned to the target push users, in order to effectively supervise the service push process of the agents, after sending the outbound user sublist to the corresponding agent terminal in step A6, the following steps are further included:

[0081] If the processing status of the outbound push task corresponding to the target push user is completed, obtain the call voice information corresponding to the outbound push task;

[0082] Performing text conversion on the acquired call voice information to obtain call text information;

[0083] If the converted call text information does not match the target push service targeted by the outbound call push task, a push exception prompt message is generated and sent to the corresponding agent terminal.

[0084] Specifically, by converting the call voice information corresponding to the outbound call push task into text and obtaining the corresponding call text information, it is possible to effectively supervise the service push process of the agent, and prevent the agent from not pushing the service in accordance with the target push service matched to the target push user, thereby serving as a basis for verifying whether the agent has violated the regulations, and preventing the agent from concentrating on pushing services that are easier to push.

[0085] In the embodiment of the present application, precisely because in the process of generating the list of users to be pushed, the candidate user list is first filtered out of non-target push users, and then the target push users screened out by the risk filtering are assigned target push services and designated agent terminals; then, the outbound push tasks corresponding to the target push users are displayed on the visual interface of the agent terminal, and the agent terminal returns corresponding task processing feedback information based on the agent's input operation on the outbound push task, and by matching the call text information with the target push service, it is possible to achieve full tracking and targeted service push before (i.e., the generation process), during and after the processing of the outbound push task, thereby avoiding multiple agents pushing services that are easier to push at the same time.

[0086] In specific implementation, after converting the call text information based on the call voice information, not only can the call voice information corresponding to the outbound push task be determined based on the call text information corresponding to the outbound push task, whether it matches the target push service, and then decide whether to generate a push exception prompt message; the user response category of the target push user can also be determined based on the call text information corresponding to the outbound push task. For example, the user response category may include agree, need to consider, or reject. For example, the user response category may also include very interested, interested, need to consider, not interested, or disgusted; then, based on the user response category of the target push user, the proportion of each user response category of P target push users in the candidate user list is determined, or the user response category of the target push user in the historical push user list is used as a reference information in the target reference information for determining the target push service corresponding to the P target push users in the candidate user list to be processed.

[0087] Specifically, in the process of matching call text information with a target push service, the call text information can be directly compared with the target push service to obtain a matching result between the call text and the push service. In order to improve the efficiency and accuracy of matching the call text information with the target push service, a first recognition model can be pre-trained, and the call text information corresponding to a certain outbound call push task can be input into the trained first recognition model to obtain a predicted push service. If the predicted push service is different from the target push service, it is determined that the converted call text information does not match the target push service targeted by the outbound call push task.

[0088] Specifically, in the process of determining the user response category of the target push user based on the call text information corresponding to the outbound call push task, call keywords can be directly extracted from the call text information, and the user response category of the target push user can be determined based on the call keywords. In order to improve the efficiency and accuracy of determining the user response category, a second recognition model can also be pre-trained, and the call text information corresponding to a certain outbound call push task can be input into the trained second recognition model to obtain the user response category.

[0089] In addition, it should be noted that the user response category can be determined based on the call text information corresponding to the outbound call push task; wherein, since the above-mentioned second feedback information represents the target push user's acceptance of the target push service, that is, the second feedback information and the user response category have a certain correspondence, therefore, the user response category can also be determined based on the second feedback information. Specifically, the correspondence between the target push user's acceptance of the target push service and the user response category can be pre-stored. For example, if the acceptance level is in the first interval value, the corresponding user response category is agreement; if the acceptance level is in the second interval value, the corresponding user response category is needs to be considered; if the acceptance level is in the third interval value, the corresponding user response category is rejection.

[0090] Furthermore, considering that the user attribute information of the target push user may change, for example, in the case of loan business, if the credit information of the target push user changes, the target push user's outstanding amount changes; or in the case of online shopping business, if the delivery address of the target push user changes, the target push user's available post-payment credit limit changes, etc., based on this, in the above step A6, after sending the above-mentioned outbound call user sub-list to the corresponding seat terminal, the following is also included:

[0091] Obtaining user attribute change information of the third target push user; if the processing status of the outbound push task corresponding to the third target push user is incomplete, determining whether the third target push user has become a non-target push user based on the user attribute change information and a preset filtering rule engine;

[0092] If the judgment result is yes, a task deletion prompt message is sent to the designated agent terminal corresponding to the third target push user; wherein the task deletion prompt message is used to instruct the designated agent terminal to delete the outbound call push task corresponding to the third target push user on the visual interface.

[0093] Specifically, after determining that the target push user has become a non-target push user based on the latest user attribute change information, if the outbound user sub-list has not been sent to the corresponding agent terminal, the push information record corresponding to the target push user in the list of users to be pushed will be directly deleted; if the outbound user sub-list has been sent to the corresponding agent terminal and the processing status of the outbound push task corresponding to the target push user is incomplete, the designated agent terminal can be triggered in time to delete the corresponding outbound push task. In this way, even if the outbound user sub-list has been sent to the corresponding agent terminal and the corresponding outbound push task has been generated at the agent terminal, the agent terminal can be triggered in time to delete the outbound push task that has changed from the target push user to the non-target push user due to the change of user attributes, stop pushing business to the user, and further improve the accuracy of business push.

[0094] In specific implementation, the outbound call push task can be deleted without the agent's awareness. However, considering that it is possible that during the conversation between the agent and the user (i.e., during the outbound call push task processing), it is determined that the target push user has become a non-target push user. Therefore, after determining that the third target push user has become a non-target push user, it also includes: determining the risk level of the third target push user based on the user attribute change information, and generating user risk warning information based on the risk level of the third target push user; wherein, the user risk warning information is used to instruct the designated agent terminal to prompt the agent on the visual interface in a preset prompting manner that the third target push user has become a non-target push user. Push user, the preset prompt method is related to at least one of the reminder intensity and reminder duration corresponding to the risk level of the third target push user, so as to attract the attention of the agent and inform the reason for deletion of the corresponding outbound push task; in addition, if it is determined that the third target push user is still the target push user and the current time period belongs to the third target push user's willingness to answer the call time period, then the task processing prompt information can be sent to the designated agent terminal corresponding to the above-mentioned third target push user; wherein, the task processing prompt information is used to instruct the designated agent terminal to prompt the user to process the outbound push task corresponding to the third target push user in a countdown prompt manner on the visual interface.

[0095] Furthermore, in order to improve the accuracy of assigning the target push service and designated agent terminal to the target push user, the target reference information may include not only the source channel identifier of the target push user, but also the user feature data and historical behavior data of the target push user.

[0096] Correspondingly, the above S206, based on the target reference information of each target push user, determines the target push service and designated agent terminal assigned to the target push user, specifically including:

[0097] Step B1, determining a target push service for the target push user based on the source channel identifier and historical behavior data of the target push user;

[0098] Specifically, the first implementation method is to determine the first alternative push service based on the above-mentioned first correspondence and the source channel identifier of the target push user, and determine the second alternative push service based on the historical behavior data of the target push user, and determine the target push service of the target push user based on the first alternative push service and the second alternative push service; wherein, the second alternative push service can be obtained by inputting the historical behavior data of the target push user into a pre-trained third recognition model, and the target push service of the target push user may include the union or intersection of the first alternative push service and the second alternative push service; the second implementation method is to pre-store the second correspondence between the source channel identifier and the historical behavior data and the identifier of the service to be pushed, and then determine the target push service of the target push user based on the second correspondence, the source channel identifier and the historical behavior data of the target push user; the third implementation method is to input the source channel identifier and the historical behavior data of the target push user into the pre-trained fourth recognition model for push service matching to obtain the target push service of the target push user.

[0099] Step B2: determining the user importance level of the target push user based on the source channel identifier and user characteristic data of the target push user, and determining a designated agent terminal corresponding to a business service level matching the user importance level.

[0100] Specifically, the first user level can be determined based on the correspondence between the source channel identifier and the user importance level and the source channel identifier of the target push user, and the second user level can be determined based on the user characteristic data of the target push user, and the user importance level of the target push user can be determined based on the first user level and the second user level; wherein, the second user level can be obtained by inputting the user characteristic data of the target push user into the pre-trained sixth recognition model, and the user importance level of the target push user can include the highest user level or the lowest user level among the first user level and the second user level; the source channel identifier and user characteristic data of the target push user can also be directly input into the pre-trained seventh recognition model to perform user level prediction to obtain the user importance level of the target push user; then, based on the third correspondence and the user importance level of the target push user, the business service level of the agent terminal is determined; and the designated agent terminal assigned to the target push user is selected from the agent terminals with this business service level.

[0101] Furthermore, the target reference information may include not only the source channel identifier, user characteristic data and historical behavior data of the target push user, but also the associated characteristic information of the preset access portal corresponding to the user source channel triggered by the target push user may reflect the type of business that the user is interested in. Therefore, the target reference information may also include the associated characteristic information of the preset access portal triggered by the target push user. The associated characteristic information may include at least one of the application type to which the preset access portal belongs and the content of the page where it is located. For example, if a user visits a preset advertising link on a news reading application, the application type to which the preset access portal belongs is information, and the content of the page where it is located includes the content of the current page that displays the preset advertising link. Specifically, Still taking the first implementation method mentioned above as an example, the reference information of each target item is used as a push service matching dimension, and then the target push service is determined based on the alternative push services corresponding to multiple push service matching dimensions; that is, the target push service assigned to the target push user is determined based on the above-mentioned first alternative push service, second alternative push service and third alternative push service, and the third alternative push service is determined based on the associated feature information of the preset access entrance triggered by the target push user. For example, the associated feature information of the target push user is input into the pre-trained fifth recognition model, and the target push service of the target push user may include the union or intersection of the first alternative push service, the second alternative push service and the third alternative push service.

[0102] Furthermore, considering that the target push user and the associated users of the target push user (i.e., other target push users that have a certain association relationship with the target push user) have certain similarities in the user response categories to the business push events, the target reference information may also include the user response categories of the associated users of the target push user; wherein, the associated users of the target push user are determined based on pre-built user association relationship graph data, the user association relationship graph data includes multiple user nodes and connection edges between user nodes that have an association relationship under a preset association dimension, and the associated users of the target push user include at least one of a first-degree associated user, a second-degree associated user, and a third-degree associated user; specifically, still taking the first implementation method as an example, each item The reference information is used as a push service matching dimension, and the target push service is determined based on the alternative push services corresponding to the multiple push service matching dimensions. That is, the target push service assigned to the target push user is determined based on the above-mentioned first alternative push service, second alternative push service and fourth alternative push service. The fourth alternative push service is determined based on the target push service corresponding to the associated user whose user response category is a preset response category. The preset response category includes user response categories that characterize that the user's acceptance of the target push service is greater than a preset threshold, for example, agree, need to consider, very interested, interested, and need to consider. For example, the target push service that most associated users are interested in is determined as the fourth alternative push service for the target push user.

[0103] In the embodiment provided by the present application, the above-mentioned target reference information includes first reference information for determining the target push service and second reference information for determining the designated agent terminal, wherein the first reference information includes the source channel identifier of the target push user, historical behavior data, associated feature information of the triggered preset access portal, and at least one of the user response categories of the associated user, and the second reference information includes the source channel identifier and at least one of the user feature data of the target push user; since the target push service and designated agent terminal corresponding to the target push user are automatically determined based on multi-dimensional reference information, the accuracy of the target push service and the designated agent terminal is further improved.

[0104] In specific implementation, Figure 5 As shown, another specific implementation principle diagram of the above information processing method is given, taking the first reference information for determining the target push service including the source channel identifier of the target push user, historical behavior data, associated feature information of the triggered preset access portal, and user response category of the associated user, and the second reference information for determining the designated agent terminal including the source channel identifier and user feature data of the target push user as an example, in the above Figure 3Based on the target reference information of each target push user, determining the target push service and designated agent terminal assigned to the target push user specifically includes:

[0105] For each target push user, a first alternative push service is determined based on the source channel identifier of the target push user; a second alternative push service is determined based on the historical behavior data of the target push user; a third alternative push service is determined based on the associated feature information of the preset access portal triggered by the target push user; and a fourth alternative push service is determined based on the user response category of the target push user's associated users;

[0106] Determine the target push service allocated to the target push user based on the first alternative push service, the second alternative push service, the third alternative push service, and the fourth alternative push service;

[0107] Based on the source channel identifier of the target push user, a first user level is determined; based on the user characteristic data of the target push user, a second user level is determined; based on the first user level and the second user level, a user importance level of the target push user is determined, and a designated agent terminal corresponding to a business service level matching the user importance level is determined.

[0108] The information processing method in the embodiment of the present application, after obtaining a list of candidate users to be processed from multiple source channels, first filters non-target push users among N candidate push users based on a preset filtering rule engine to obtain P target push users, and then determines the target push service and designated agent terminal assigned to the target push user based on the target reference information of the target push user; then generates a list of users to be pushed based on the target push services and designated agent terminals corresponding to the P target push users, so that each designated agent terminal can push services to its assigned target push users in a targeted manner; that is, in the process of determining the list of users to be pushed, the candidate user list is first filtered for non-target push users, and then the target push users selected by the risk filtering are assigned target push services and designated agent terminals. This not only improves the pertinence and accuracy of service push, thereby improving the user answering experience, but also avoids the problem of wasting agent resources due to targeting users with risk levels greater than a preset threshold as target push users, thereby improving agent utilization.

[0109] Corresponding to the above Figures 2 to 5 The information processing method described above is based on the same technical concept. The embodiment of the present application also provides an information processing device. Figure 6 This is a schematic diagram of the first module composition of the information processing device provided in the embodiment of the present application, which is used to perform Figures 2 to 5 Describes information processing methods such as Figure 6 As shown, the device includes:

[0110] The list acquisition module 602 is used to obtain a list of candidate users to be processed; the candidate user list includes N candidate push users from multiple source channels, where N is an integer greater than 1;

[0111] The first determining module 604 is configured to filter non-target push users from the N candidate push users based on a preset filtering rule engine to obtain P target push users, where P is an integer greater than 1 and less than N.

[0112] The second determining module 606 is configured to determine the target push service and designated agent terminal assigned to the target push user based on the target reference information of each target push user; the target reference information includes a source channel identifier of the target push user;

[0113] The list generation module 608 is used to generate a list of users to be pushed based on the target push service and designated agent terminal corresponding to each target push user; the list of users to be pushed includes an outbound user sublist of each agent terminal.

[0114] The information processing device in the embodiment of the present application, after obtaining a list of candidate users to be processed from multiple source channels, first filters non-target push users among N candidate push users based on a preset filtering rule engine to obtain P target push users, and then determines the target push service and designated agent terminal assigned to the target push user based on the target reference information of the target push user; then generates a list of users to be pushed based on the target push services and designated agent terminals corresponding to the P target push users, so that each designated agent terminal can push services to its assigned target push users in a targeted manner; that is, in the process of determining the list of users to be pushed, the candidate user list is first filtered for non-target push users, and then the target push users selected by the risk filtering are assigned target push services and designated agent terminals. This not only improves the pertinence and accuracy of service push, thereby improving the user answering experience, but also avoids the problem of wasting agent resources due to targeting users with risk levels greater than a preset threshold as target push users, thereby improving the utilization rate of agent personnel.

[0115] It should be noted that the embodiment of the information processing device in this application and the embodiment of the information processing method in this application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding information processing method mentioned above, and the repeated parts will not be repeated.

[0116] Furthermore, corresponding to the above Figures 2 to 5The method shown in FIG. 1 is based on the same technical concept. The embodiment of the present application also provides an information processing device, which is used to execute the above-mentioned information processing method. Figure 7 shown.

[0117] The information processing device may have relatively large differences due to different configurations or performances, and may include one or more processors 701 and memory 702, and the memory 702 may store one or more storage applications or data. Among them, the memory 702 can be a temporary storage or a persistent storage. The application stored in the memory 702 may include one or more modules (not shown in the figure), each module may include a series of computer-executable instructions for the information processing device. Furthermore, the processor 701 can be configured to communicate with the memory 702 to execute a series of computer-executable instructions in the memory 702 on the information processing device. The information processing device may also include one or more power supplies 703, one or more wired or wireless network interfaces 704, one or more input and output interfaces 705, one or more keyboards 706, etc.

[0118] In a specific embodiment, an information processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the information processing device, and the one or more programs are configured to be executed by one or more processors, including computer-executable instructions for performing the following:

[0119] Obtain a list of candidate users to be processed; the list of candidate users includes N candidate push users from multiple source channels, where N is an integer greater than 1;

[0120] Filtering non-target push users from the N candidate push users based on a preset filtering rule engine to obtain P target push users; P is an integer greater than 1 and less than N;

[0121] Determine the target push service and designated agent terminal assigned to the target push user based on the target reference information of each target push user; the target reference information includes the source channel identifier of the target push user;

[0122] Based on the target push service and designated agent terminal corresponding to each target push user, a list of users to be pushed is generated; the list of users to be pushed includes a sub-list of outbound users of each agent terminal.

[0123] The information processing device in the embodiment of the present application, after obtaining a list of candidate users to be processed from multiple source channels, first filters non-target push users from N candidate push users based on a preset filtering rule engine to obtain P target push users, and then determines the target push service and designated agent terminal assigned to the target push user based on the target reference information of the target push user; then generates a list of users to be pushed based on the target push services and designated agent terminals corresponding to the P target push users, so that each designated agent terminal can push services to its assigned target push users in a targeted manner; that is, in the process of determining the list of users to be pushed, the candidate user list is first filtered for non-target push users, and then the target push users selected by the risk filtering are assigned target push services and designated agent terminals. This not only improves the pertinence and accuracy of service push, thereby improving the user answering experience, but also avoids the problem of wasting agent resources due to targeting users with risk levels greater than a preset threshold as target push users, thereby improving the utilization rate of agent personnel.

[0124] It should be noted that the embodiment of the information processing device in this application and the embodiment of the information processing method in this application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding information processing method mentioned above, and the repeated parts will not be repeated.

[0125] Furthermore, corresponding to the above Figures 2 to 5 The method shown is based on the same technical concept. The embodiment of the present application also provides a storage medium for storing computer-executable instructions. In a specific embodiment, the storage medium can be a USB flash drive, an optical disk, a hard disk, etc. When the computer-executable instructions stored in the storage medium are executed by the processor, the following process can be implemented:

[0126] Obtain a list of candidate users to be processed; the list of candidate users includes N candidate push users from multiple source channels, where N is an integer greater than 1;

[0127] Filtering non-target push users from the N candidate push users based on a preset filtering rule engine to obtain P target push users; P is an integer greater than 1 and less than N;

[0128] Determine the target push service and designated agent terminal assigned to the target push user based on the target reference information of each target push user; the target reference information includes the source channel identifier of the target push user;

[0129] Based on the target push service and designated agent terminal corresponding to each target push user, a list of users to be pushed is generated; the list of users to be pushed includes a sub-list of outbound users of each agent terminal.

[0130] When the computer-executable instructions stored in the storage medium in the embodiment of the present application are executed by the processor, after obtaining a list of candidate users to be processed from multiple source channels, the processor first filters non-target push users from N candidate push users based on a preset filtering rule engine to obtain P target push users, and then determines the target push services and designated agent terminals assigned to the target push users based on the target reference information of the target push users; then, based on the target push services and designated agent terminals corresponding to the P target push users, a list of users to be pushed is generated. In this way, each designated agent terminal can push services to its assigned target push users in a targeted manner; that is, in the process of determining the list of users to be pushed, the candidate user list is first filtered for non-target push users, and then the target push users selected by the risk filtering are assigned target push services and designated agent terminals. This not only improves the pertinence and accuracy of service push, thereby enhancing the user's call answering experience, but also avoids the problem of wasting agent resources due to targeting users with risk levels greater than a preset threshold as target push users, thereby improving agent utilization.

[0131] It should be noted that the embodiment of the storage medium in this application and the embodiment of the information processing method in this application are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the corresponding information processing method mentioned above, and the repeated parts will not be repeated.

[0132] The foregoing description describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0133] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the embodiments of the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0137] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-permanent storage in a computer-readable medium, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0138] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0139] It should also be noted that the terms "comprises," "includes," or any other variants thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity, or device. In the absence of further restrictions, an element defined by the statement "comprises one..." does not exclude the presence of other identical elements in the process, method, commodity, or device comprising the element. The embodiments of the present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. One or more embodiments of the present application can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0140] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The above is only an embodiment of this document and is not intended to limit this document. For those skilled in the art, this document may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this document should be included in the scope of the claims of this document.

Claims

1. An information processing method, characterized in that: The method comprises: Obtain a list of candidate users to be processed; the list of candidate users includes N candidate push users from multiple source channels, where N is an integer greater than 1; Filtering non-target push users from the N candidate push users based on a preset filtering rule engine to obtain P target push users; P is an integer greater than 1 and less than N; Based on the target reference information of each target push user, a target push service and a designated agent terminal that match the target push user are assigned to the target push user; the target reference information includes the source channel identifier of the target push user, user feature data, historical behavior data, and associated feature information of the preset access portal triggered by the target push user; Generate an initial push user list based on the target push service and designated agent terminal corresponding to each target push user; Based on the initial push user list and the historical push user list, a list of users to be pushed is generated; the list of users to be pushed includes a sub-list of outbound users of each agent terminal; the initial push user list includes the P target push users, and the historical push user list includes multiple historical push users determined based on a candidate user list obtained within a preset historical time period; if the current processing status of the outbound push tasks corresponding to the repeated push users in the initial push user list and the historical push user list is incomplete, the target push service corresponding to the repeated push user in the initial push user list is also added to the push service set of the repeated push user in the historical push user list.

2. The method according to claim 1, characterized in that The list of users to be pushed does not include the target push users included in the list of historical push users.

3. The method according to claim 1, characterized in that After generating a list of users to be pushed based on the initial push user list and the historical push user list, the method further includes: Determine the current processing status of the outbound push tasks corresponding to the repeated push users in the initial push user list and the historical push user list; If the current processing status is unfinished, determining whether the first push service and the second push service of the repeatedly pushed user are the same; wherein the first push service includes the target push service of the repeatedly pushed user in the initial push user list, and the second push service includes the target push service of the repeatedly pushed user in the historical push user list; If they are not the same, the target push service of the repeated push user in the historical push user list is updated based on the first push service.

4. The method according to claim 1, wherein After generating a list of users to be pushed based on the initial push user list and the historical push user list, the method further includes: Sending the outbound user sublist to the corresponding agent terminal; the outbound user sublist is used to instruct the agent terminal to generate an outbound push task corresponding to each target push user, and displaying the outbound push task on a visual interface; Receive task processing feedback information sent by the agent terminal for the outbound call push task, and perform corresponding information processing operations based on the task processing feedback information.

5. The method according to claim 4, characterized in that The performing corresponding information processing operations based on the task processing feedback information includes: If the task processing feedback information includes first feedback information indicating that the outbound call push task for the first target push user has been completed, updating the processing status of the outbound call push task for the first target push user based on the first feedback information; If the task processing feedback information includes second feedback information representing the target push user's acceptance level of the target push service, then based on the second feedback information, determine the second target push user whose acceptance level is less than a preset threshold; and based on the user identification information of the second target push user, update the filtering rule set in the filtering rule engine.

6. The method according to claim 4, characterized in that After sending the outbound user sublist to the corresponding agent terminal, the method further includes: If the processing status of the outbound call push task corresponding to the target push user is completed, obtaining the call voice information corresponding to the outbound call push task; Performing text conversion on the call voice information to obtain call text information; If the call text information does not match the target push service targeted by the outbound call push task, a push exception prompt message is generated and sent to the corresponding agent terminal.

7. The method according to claim 1, characterized in that The allocating a target push service and a designated agent terminal that match the target push user based on the target reference information of each target push user includes: Determining a target push service for the target push user based on a source channel identifier and historical behavior data of the target push user; and Based on the source channel identifier and user characteristic data of the target push user, the user importance level of the target push user is determined, and a designated agent terminal corresponding to a business service level matching the user importance level is determined.

8. An information processing device, characterized in that The device comprises: A list acquisition module is used to obtain a list of candidate users to be processed; the candidate user list includes N candidate push users from multiple source channels, where N is an integer greater than 1; A first determining module is configured to filter non-target push users from the N candidate push users based on a preset filtering rule engine to obtain P target push users; P is an integer greater than 1 and less than N; a second determination module configured to assign a target push service and a designated agent terminal that matches the target push user based on target reference information of each target push user; the target reference information including a source channel identifier, user feature data, historical behavior data, and associated feature information of a preset access portal triggered by the target push user; The list generation module is used to generate an initial push user list based on the target push services and designated agent terminals corresponding to each of the target push users, and to generate a list of users to be pushed based on the initial push user list and the historical push user list; the list of users to be pushed includes a sub-list of outbound users of each agent terminal; the initial push user list includes the P target push users, and the historical push user list includes multiple historical push users determined based on a candidate user list obtained within a preset historical time period; if the current processing status of the outbound push tasks corresponding to the repeated push users in the initial push user list and the historical push user list is incomplete, the target push service corresponding to the repeated push user in the initial push user list is also added to the push service set of the repeated push user in the historical push user list.

9. An information processing device, characterized in that The device comprises: processor; and A memory arranged to store computer executable instructions, the executable instructions being configured to be executed by the processor, the executable instructions comprising instructions for performing the steps of the method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is used to store computer-executable instructions, and the executable instructions enable a computer to execute the method according to any one of claims 1 to 7.

Images