Outbound method and device based on clue operation, equipment and storage medium
By receiving and filtering call clues in the intelligent outgoing call system and issuing job instructions based on the screening results, the problem of difficulty in distinguishing high and low quality clues in traditional systems is solved, and efficient resource utilization and balance of outgoing call revenue and user satisfaction are achieved.
Patent Information
- Application Number
- CN202510106961.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-23
- Publication Date
- 2025-04-25
AI Technical Summary
Traditional intelligent outgoing calls cannot effectively distinguish high-quality clues from low-quality clues, resulting in waste of resources. The system has limited ability to track and analyze clues, making it difficult to achieve effective clue operation management, and it is difficult to balance outgoing calls revenue and user satisfaction.
By receiving the call clues and marking their status as being issued, the call clues are analyzed and filtered based on the filtering rules and/or the quantitative model, the job instructions are issued to the outgoing call system, the call clues are marked as issued status, and the outgoing call system is instructed to perform outgoing call jobs according to the issuance cycle of the call clues.
Effective lead operation management is achieved, resource waste is avoided, and outgoing calls can be effectively balanced.
Smart Images
Figure CN119892983A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of outbound call processing, and in particular to an outbound call method, device, equipment and storage medium based on lead operation. Background Art
[0002] Outbound calls are a form of communication in which modern customer service center systems actively initiate calls to customers. Currently, intelligent outbound call systems are widely used in marketing, customer service, and information collection. These systems can automatically make calls to communicate with potential or existing customers. However, traditional intelligent outbound call systems cannot effectively distinguish between high-quality leads and low-quality leads, resulting in a waste of resources. At the same time, the system's ability to track and analyze leads is limited, making it difficult to achieve effective lead operation management, resulting in a difficult balance between outbound call revenue and user satisfaction during the outbound call process. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide an outbound calling method, device, equipment and storage medium based on lead operation, so as to solve the problem that traditional intelligent outbound calling systems usually lack effective data analysis and user lead operation mechanisms, resulting in difficulty in balancing outbound calling revenue and user satisfaction during the outbound calling process.
[0004] In a first aspect, an embodiment of the present application provides an outbound calling method based on lead operation, comprising:
[0005] Receive a call clue and mark the state of the call clue as a pending state;
[0006] Analyze and screen call leads based on screening rules and / or quantitative models;
[0007] After sending the operation instructions to the outbound call system according to the screened call leads, the call leads are marked as sent; wherein the operation instructions include call batches and call cycles;
[0008] Instruct the outbound call system to perform outbound call operations according to the call lead delivery cycle.
[0009] In the above implementation process, call leads are received and the status of the call leads is marked as a pending status; the call leads are analyzed and screened based on screening rules and / or quantitative models; after sending operation instructions to the outbound call system based on the screened call leads, the call leads are marked as a sent status; wherein the operation instructions include call batches and call cycles; the outbound call system is instructed to perform outbound call operations according to the sending cycle of the call leads; the call system is tracked throughout the entire cycle, and the call leads are analyzed and screened at the same time, and call operations are performed based on the screened call leads, so as to avoid waste of resources, realize effective lead operation management, and effectively balance outbound call revenue and user satisfaction.
[0010] Further, the instructing the outbound call system to perform an outbound call operation according to the sending cycle of the call clues includes:
[0011] Instructing the outbound call system that the number of outbound calls or connections in a call clue delivery cycle does not exceed a first set number threshold and the number of outbound calls or connections per day does not exceed a second set number threshold;
[0012] The call feedback result is received, and a plurality of outbound call intention types are generated, wherein the outbound call intention types include intention degree levels.
[0013] In the above implementation process, making calls according to the sending cycle of call leads can effectively balance outbound call revenue and user satisfaction. According to the outbound call intention type generated by the call feedback results, the call leads can be adjusted to achieve effective lead operation management.
[0014] Furthermore, it also includes:
[0015] Detecting that the cycle of the call thread ends, marking the call thread as frozen;
[0016] Set a freeze period based on project requirements;
[0017] Set a freeze period based on the outbound call intent type.
[0018] In the above implementation process, a call freeze period is set, that is, a waiting time for a call is set to prevent users from being served frequently and avoid affecting user satisfaction.
[0019] Furthermore, it also includes:
[0020] When the freezing period ends, the call lead is marked as pending for dispatch;
[0021] When the call lead has experienced a freezing period, the call lead is analyzed and screened based on screening rules and / or quantitative models.
[0022] In the above implementation process, if the call lead has passed the freezing period, the call lead is screened and then a call is made based on the lead, and the call lead is tracked throughout the entire cycle to achieve effective lead operation management.
[0023] Furthermore, the analyzing and screening of call leads based on screening rules and / or quantitative models includes:
[0024] Get screening features from call leads;
[0025] Analyze and screen call leads based on screening features and combined with screening rules;
[0026] and / or,
[0027] Input the call leads to the trained quantitative model, and analyze and sort the call leads according to the output results by the quantitative model to divide the call batches; wherein the output results include scoring scores or importance levels.
[0028] In the above implementation process, call leads are analyzed and screened through screening rules and quantitative models to avoid waste of resources, which can effectively balance outbound call revenue and user satisfaction.
[0029] Furthermore, before analyzing and screening the call leads based on the screening rules and / or the quantitative model, the method further includes:
[0030] Obtain an initial quantitative model;
[0031] Extract objective labels from call leads;
[0032] The initial quantization model is iterated for the first time according to the objective label to obtain a quantization model of the first iteration.
[0033] In the above implementation process, the quantitative model is iterated through objective labels to ensure that the screening results of the quantitative model for call leads are more accurate.
[0034] Furthermore, when the call lead has experienced a freezing period, before analyzing and screening the call lead based on screening rules and / or quantitative models, the method further includes:
[0035] The quantization model is iterated for a second time according to the objective labels and the subjective labels to obtain a second-iteration quantization model; wherein the proportion of subjective labels in the label data used to train the quantization model is greater than the proportion of objective labels.
[0036] In the above implementation process, the quantitative model is iterated by combining objective labels with subjective labels. At the same time, subjective labels are more instructive for the screening of call leads, and therefore account for a higher proportion; more accurate screening of call leads is achieved, which is conducive to improving call revenue and user satisfaction.
[0037] In a second aspect, an embodiment of the present application provides an outbound calling device based on clue operation, including:
[0038] A clue receiving module, used for receiving a call clue and marking the state of the call clue as a pending state;
[0039] A lead screening module, for analyzing and screening call leads based on screening rules and / or quantitative models;
[0040] The call issuing module is used to issue the operation instruction to the outbound call system according to the screened call clues, and mark the call clues as issued; wherein the operation instruction includes the call batch and the call cycle;
[0041] The operation instruction module is used to instruct the outbound call system to perform outbound call operations according to the sending cycle of the call clues.
[0042] In a third aspect, an embodiment of the present application provides an electronic device, including:
[0043] A processor, a memory and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, they are used to implement the outbound calling method based on lead operation as described above.
[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a server, the outbound calling method based on lead operation as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0046] Figure 1 A flowchart of an outbound calling method based on lead operation provided in an embodiment of the present application;
[0047] Figure 2 It is a structural schematic diagram of an outbound calling device based on clue operation provided in an embodiment of the present application;
[0048] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0049] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0050] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0051] Please see Figure 1 , Figure 1 A flowchart of an outbound calling method based on lead operation provided in an embodiment of the present application. The outbound calling method based on lead operation includes:
[0052] 100. Receive a call clue and mark the state of the call clue as a pending state.
[0053] Specifically, the call leads sent by the lead provider are received through the operation system of the lead operation outbound caller. The call leads can come from multiple channels, such as website form submission, telephone hotline, social media, advertising campaigns, etc.; optionally, after the call leads are initially processed, the status of the call leads is marked from the unprocessed status to the pending status (the status can be marked by remark information or other means).
[0054] The initial processing of call leads may include data collection, preliminary selection, data cleaning, etc. The purpose of preliminary selection is to exclude invalid or unqualified leads, and the purpose of data cleaning is to check and correct errors in the data, such as spelling errors, inconsistent formats, etc.
[0055] Among them, call leads may include the user's calling method, user feature information, user demand information, etc. The life cycle of a call lead is a complete process from collection to final transaction (or failure), including multiple stages such as warehousing, outbound call operation, and transaction.
[0056] 200. Analyze and screen call leads based on screening rules and / or quantitative models.
[0057] Specifically, screening rules are used to preliminarily filter and screen call leads, and quantitative models are used to more accurately analyze and screen call leads; optionally, analysis and screening of call leads may include screening of source channels, screening of customer characteristics, and screening of demand matching.
[0058] Among them, the screening of source channels: the quality of leads from different source channels may vary. Enterprises can score or stratify leads from different channels based on historical data and expert experience, and give priority to leads from high-scoring channels. Among them, the screening of customer characteristics: screening based on the characteristics of potential customers (such as age, gender, occupation, income level, etc.) to determine which customers with which characteristics are more likely to be interested in products or services. Among them, the screening of demand matching: analyzing the needs of potential customers and matching them with the company's products or services. Only those leads whose needs are highly matched with the company's products or services are worth further follow-up.
[0059] 210. Obtain screening features from call leads.
[0060] Specifically, the call clue may include the user's contact information, the user's characteristic information, the user's demand information, etc., so the user's characteristic information and the user's demand information can be obtained as screening features.
[0061] 220. Analyze and screen call leads based on screening features and combined with screening rules.
[0062] Optionally, the screening rules are formed based on the historical experience of the operating system, that is, the historical call leads and the data of the entire cycle of calls made through the call leads are analyzed to form the screening rules, which specifically show which screening features correspond to users who may be interested in the product or service, and exclude users who obviously do not meet the screening features (that is, users are not interested in the product or service at all).
[0063] Optionally, the screening features may include age, gender, city, past experience of purchasing products or services, historical browsing history, etc.
[0064] Exemplarily, the user has browsed the service three times in history, and the historical experience in the screening rules shows that most users (which can be set according to needs, for example, 80% of users) have browsed the service two or more times and the call results are all "interested in the service", then the call clue will be retained; Exemplarily, the user has browsed the service once in history and evaluated the service as not interested, and the historical experience in the screening rules shows that the call results of users who made this operation are all "not interested in the service", then the call clue will be removed.
[0065] For example, if the user's age group or gender is not within the service target range of the service, the call lead will be removed.
[0066] 230. And / or, inputting the call leads into the trained quantitative model, analyzing and sorting the call leads according to the output results by the quantitative model to divide the call batches; wherein the output results include scoring scores or importance levels.
[0067] It can be understood that all call leads are input into the trained quantitative model, the quantitative model performs training and analysis on all call leads, generates corresponding output results, and sorts all call leads according to the output results, so that the call leads can be called in order and periodically in the future. Optionally, the output results include scoring scores or importance levels, that is, the quantitative model generates multiple scoring scores after training the call leads, and the call leads are sorted according to the scoring scores, or the quantitative model generates multiple importance levels after training the call leads, and the call leads are sorted according to the importance levels.
[0068] Therefore, by analyzing and screening call leads through screening rules and quantitative models, waste of resources can be avoided, and outbound call revenue and user satisfaction can be effectively balanced.
[0069] 300. After issuing a work instruction to the outbound call system according to the screened call clues, the call clues are marked as issued; wherein the work instruction includes a call batch and a call cycle.
[0070] It should be noted that the filtered call leads are sorted in a set order, and the operation instructions are set according to specific operation requirements, including dividing the call leads into several call batches according to the sorting order, and calling them in sequence, including setting a call cycle for the call leads, that is, performing a call operation at each set interval. It can be understood that the call batch and the call cycle can be set according to specific needs, and the embodiment of the present application does not limit the specific values of the call batch and the call cycle.
[0071] 400. Instruct the outbound call system to perform an outbound call operation according to the sending cycle of the call clue.
[0072] 410. Instruct the outbound call system that the number of outbound calls or connections in a call clue delivery cycle does not exceed a first set number threshold and the number of outbound calls or connections per day does not exceed a second set number threshold.
[0073] It should be noted that the specific values of the sending cycle, the first set number threshold and the second set number threshold are all set according to specific job call requirements.
[0074] For example, the number of outbound calls or connected calls by a call lead does not exceed 1 per day, so as to avoid the user feeling that they are being served too frequently, which affects the user satisfaction.
[0075] 420. Receive call feedback results and generate multiple outbound call intention types, wherein the outbound call intention types include intention degree levels.
[0076] It is understandable that during the outbound call process, there may be cases where users have low service intentions or complaints, and thus call feedback results are received. After marking, they can be set to multiple outbound call intention types, specifically multiple intention levels, so that the user's freeze period can be set according to the intention level, or users can be screened according to the intention level, as well as the screening rules and quantitative models can be adjusted and optimized according to the intention level.
[0077] Exemplarily, the intention level is set to 1-5 levels according to the user's dissatisfaction to very satisfaction, where level 1 means the user is very dissatisfied, level 2 means the user is dissatisfied, level 3 means the user has a moderate attitude, level 4 means the user is satisfied, and level 5 means the user is very satisfied.
[0078] Therefore, making calls according to the call lead delivery cycle can effectively balance outbound call revenue and user satisfaction. According to the outbound call intention type generated by the call feedback results, the call leads can be adjusted to achieve effective lead operation management.
[0079] For example, collect contact information, demand information, behavioral data, etc. of potential customers to provide basic data for screening and analysis; perform preliminary filtering of collected leads according to screening rules to remove leads that do not meet the requirements; use quantitative models to score the leads after preliminary screening to assess their potential value and transaction probability; prioritize the leads based on the scoring results, giving priority to high-scoring, high-potential leads; and continuously adjust and optimize screening rules and quantitative models based on feedback results.
[0080] As described above, the embodiment of the present application receives call leads and marks the status of the call leads as a pending status; analyzes and screens the call leads based on screening rules and / or quantitative models; after sending a job instruction to the outbound call system based on the screened call leads, the call leads are marked as having been sent; wherein the job instruction includes a call batch and a call cycle; instructs the outbound call system to perform outbound call operations according to the sending cycle of the call leads; tracks the call system throughout the entire cycle, analyzes and screens the call leads at the same time, and performs call operations based on the screened call leads, thereby avoiding waste of resources, achieving effective lead operation management, and effectively balancing outbound call revenue and user satisfaction.
[0081] On the basis of the above embodiment, the outbound calling method based on lead operation in the embodiment of the present application can also be embodied as follows:
[0082] 510. It is detected that the cycle of the call thread ends, and the call thread is marked as frozen.
[0083] Specifically, after the call lead cycle ends, the operation system marks these cases as frozen. The purpose of marking frozen is to set a waiting time. During the frozen period, the outbound call system will not contact the users to prevent them from feeling that they are being served frequently. During the frozen period of the call lead, the operation system temporarily stops the active follow-up activities for the lead to save resources and energy; retains all relevant information and communication history of the lead for possible future analysis or reactivation; manages frozen leads separately from leads in other states to get a clearer understanding of the current sales or service status.
[0084] 520. Set a freeze period based on project requirements.
[0085] The freezing period can be dynamically adjusted according to the actual situation of each project, that is, different freezing periods can be set for call leads according to different projects, or the freezing period can be set in combination with user feature information and user demand information.
[0086] 530. Set a freeze period based on the outbound call intention type.
[0087] Optionally, the freezing period can be set differently according to the outbound call intention type. The freezing period for users with high intention is short, and the freezing period for users with low intention is appropriately increased. For example, the freezing period for customers with an intention level of 1 is set to one year, and the freezing period for customers with an intention level of 5 is set to one month.
[0088] Therefore, a call freeze period is set, that is, a waiting time for a call is set to prevent users from being served frequently and avoid affecting user satisfaction.
[0089] On the basis of the above embodiment, the outbound calling method based on lead operation in the embodiment of the present application can also be embodied as follows:
[0090] 610. It is detected that the freezing period ends, and the call clue is marked as a pending-to-be-sent state.
[0091] Specifically, if the clues have passed the freezing period, the operation system will mark the status of these cases as pending for dispatch. The cases pending for dispatch are cases that have been marked as available for call by the operation system and can be reached by the outbound calling system at any time.
[0092] 620. When the call lead has experienced a freezing period, the call lead is analyzed and screened based on screening rules and / or quantitative models.
[0093] Understandably, if a case has passed a freezing period, after screening the call leads through screening rules, the call leads can be screened based on intention level, user feature information, user demand information and historical experience; if the case has a communication record, the call system is analyzed and screened through the iterative quantitative model. The specific quantitative model combines objective labels and subjective labels to score and sort the call leads, and makes outbound calls based on the sorting results.
[0094] Therefore, if the call lead has passed the freezing period, the call lead can continue to be screened and calls can be made based on the lead, and the call lead can be tracked throughout the entire cycle to achieve effective lead operation management.
[0095] Exemplarily, the clue provider sends the clues into the operation system, at which time the operation system marks the status of these cases as "pending for dispatch"; if the clues in the "pending for dispatch" status need to be screened for outbound calls, the outbound calls can be selected based on rules and quantitative models; the selected clues are sent to the outbound call system for operation, and after successful issuance, the operation system marks the status of these cases as "issued"; the clues will generally be called out multiple times or connected multiple times within a dispatch cycle, and then this cycle ends, among which, the outbound call is made once a day, and the connection is made once a day at most; during the outbound call process, there may be cases where users have low service intentions or complaints, which can be set to multiple outbound call intention types after manual marking; after the clue issuance cycle ends, the operation system marks the status of these cases as "frozen", and the purpose of marking the freeze is to set a waiting time. During the frozen period, the outbound call system will not reach users to prevent users from feeling that they are frequently served. Among them, the freezing period can be dynamically adjusted according to the actual situation of each project, and different freezing periods can be set according to the type of outbound call intention. Users with high intentions have a short freezing period, and users with low intentions have an appropriately increased freezing period. If the clues have passed the freezing period, the operation system will mark these cases as "pending for dispatch". Cases to be dispatched are cases that the operation system has marked as ready for call and can be used at any time to reach the outbound call system. For the clues in the "pending for dispatch" status, outbound calls can also be selected based on rules and quantitative models.
[0096] On the basis of the above embodiment, the outbound calling method based on lead operation in the embodiment of the present application can also be embodied as follows: before analyzing and screening the call leads based on the screening rules and / or the quantitative model, it also includes:
[0097] Acquire an initial quantitative model; extract objective labels from call clues; perform a first iteration on the initial quantitative model according to the objective labels to obtain a quantitative model of the first iteration.
[0098] Optionally, the initial quantitative model is a quantitative model trained by the system based on historical data or specific needs. The quantitative model adopts a decision tree algorithm and inputs the user's objective label into the initial quantitative model for the first iteration, wherein the objective label may include the user's gender, user age, the city where the user is located, whether the user has purchased insurance in the past, click and browse records of related websites, etc.; thereby, the quantitative model is iterated through objective labels to ensure that the quantitative model's screening results for call leads are more accurate.
[0099] On the basis of the above embodiment, the outbound calling method based on lead operation in the embodiment of the present application can also be embodied as follows: after the call lead has experienced a freezing period, before analyzing and screening the call lead based on screening rules and / or quantitative models, it also includes:
[0100] The quantization model is iterated for a second time according to the objective labels and the subjective labels to obtain a second-iteration quantization model; wherein the proportion of subjective labels in the label data used to train the quantization model is greater than the proportion of objective labels.
[0101] Optionally, the quantitative model adopts a decision tree algorithm and inputs the user's subjective labels into the quantitative model for a second iteration, wherein the subjective labels may include whether communication has occurred, dialogue labels of the communication process, willingness to open the insurance page, willingness to receive text messages, etc., wherein subjective labels can better reflect the customer's subjective intentions than objective labels, and thus the proportion of subjective labels in the label data for training the quantitative model is greater than the proportion of objective labels; thereby, the quantitative model is iterated by combining objective labels with subjective labels, and at the same time, subjective labels are more instructive for the screening of call leads, and therefore have a higher proportion; thereby achieving more accurate screening of call leads, and facilitating the improvement of call revenue and user satisfaction.
[0102] In some embodiments, the quantitative model may include a channel quality scoring model: based on the experience of business experts or machine learning algorithms, leads from different channels are scored to evaluate their conversion potential. The quantitative model may include a dynamic scoring model: based on the behavioral data of potential customers (such as browsing history, click-through rate, dwell time, etc.) and transaction data (such as purchase history, purchase intention, etc.), leads are dynamically scored to reflect their current purchase intention and potential value. The quantitative model may include a predictive model: using machine learning algorithms such as logistic regression, decision trees, random forests, etc., a predictive model is established to predict the transaction probability of the lead. The above model can be trained and optimized based on the characteristic variables in the historical data (such as customer characteristics, behavioral data, etc.).
[0103] The above steps are not to be performed in a strict order as described in the numbers, but should be understood as an overall solution.
[0104] In the second aspect, based on the above embodiments, Figure 2 A schematic diagram of the structure of an outbound calling device based on lead operation provided in an embodiment of the present application. Figure 2 The outbound calling device based on clue operation provided in this embodiment specifically includes: a clue receiving module 201, a clue screening module 202, a call sending module 203 and an operation instruction module 204.
[0105] Among them, the clue receiving module 201 is used to receive call clues and mark the status of the call clues as a pending status; the clue screening module 202 is used to analyze and screen the call clues based on screening rules and / or quantitative models; the call sending module 203 is used to send job instructions to the outbound call system according to the screened call clues, and then mark the call clues as a sent status; wherein the job instructions include call batches and call cycles; the job instruction module 204 is used to instruct the outbound call system to perform outbound call operations according to the sending cycle of the call clues.
[0106] As described above, the embodiment of the present application receives call leads and marks the status of the call leads as a pending status; analyzes and screens the call leads based on screening rules and / or quantitative models; after sending a job instruction to the outbound call system based on the screened call leads, the call leads are marked as having been sent; wherein the job instruction includes a call batch and a call cycle; instructs the outbound call system to perform outbound call operations according to the sending cycle of the call leads; tracks the call system throughout the entire cycle, analyzes and screens the call leads at the same time, and performs call operations based on the screened call leads, thereby avoiding waste of resources, achieving effective lead operation management, and effectively balancing outbound call revenue and user satisfaction.
[0107] The outbound calling device based on lead operation provided in the embodiment of the present application can be used to execute the outbound calling method based on lead operation provided in the above embodiment, and has corresponding functions and beneficial effects.
[0108] On the third aspect, the embodiment of the present application also provides an electronic device, which can integrate the outbound calling device based on lead operation provided by the embodiment of the present application. Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 The electronic device includes: an input device 33, an output device 34, a memory 32 and one or more processors 31; the memory 32 is used to store one or more programs; when the one or more programs are executed by the one or more processors 31, the one or more processors 31 implement the outbound calling method based on lead operation as provided in the above embodiment. The input device 33, the output device 34, the memory 32 and the processor 31 can be connected by a bus or other means. Figure 3 The example of connecting through bus is taken in the following.
[0109] The processor 31 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 32, that is, realizes the above-mentioned outbound calling method based on lead operation.
[0110] The electronic device provided above can be used to execute the outbound calling method based on lead operation provided in the above embodiment, and has corresponding functions and beneficial effects.
[0111] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the outbound calling method based on lead operation as described above, and can achieve the same beneficial effects.
[0112] Of course, the storage medium containing computer executable instructions provided in the embodiment of the present application is not limited to the outbound calling method based on lead operation as described above, and can also execute related operations in the outbound calling method based on lead operation provided in any embodiment of the present application.
[0113] In a fifth aspect, the embodiments of the present application also provide a computer program product, and the methods described in the various embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the various embodiments of the present application is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM (Open Application Model) or other programmable device.
[0114] The computer program or instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it may also be an optical medium, such as a digital video disk; it may also be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.
[0115] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0116] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0117] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0118] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0119] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0120] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including 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, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
Claims
1. An outbound calling method based on lead operation, characterized in that: The method comprises: Receive a call clue and mark the state of the call clue as a pending state; Analyze and screen call leads based on screening rules and / or quantitative models; After sending the operation instructions to the outbound call system according to the screened call leads, the call leads are marked as sent; wherein the operation instructions include call batches and call cycles; Instruct the outbound call system to perform outbound call operations according to the call lead delivery cycle.
2. The outbound calling method based on lead operation according to claim 1 is characterized in that: The instructing the outbound calling system to perform an outbound calling operation according to the sending cycle of the call clues includes: Instructing the outbound call system that the number of outbound calls or connections in a call clue delivery cycle does not exceed a first set number threshold and the number of outbound calls or connections per day does not exceed a second set number threshold; The call feedback result is received, and a plurality of outbound call intention types are generated, wherein the outbound call intention types include intention degree levels.
3. The outbound calling method based on lead operation according to claim 1 is characterized in that: Also includes: Detecting that the cycle of the call thread ends, marking the call thread as frozen; Set a freeze period based on project requirements; Set a freeze period based on the outbound call intent type.
4. The outbound calling method based on lead operation according to claim 1, characterized in that: Also includes: When the freezing period ends, the call lead is marked as pending for dispatch; When the call lead has experienced a freezing period, the call lead is analyzed and screened based on screening rules and / or quantitative models.
5. The outbound calling method based on lead operation according to claim 1 is characterized in that: The analyzing and screening of call leads based on screening rules and / or quantitative models includes: Get screening features from call leads; Analyze and screen call leads based on screening features and combined with screening rules; and / or, Input the call leads to the trained quantitative model, and analyze and sort the call leads according to the output results by the quantitative model to divide the call batches; wherein the output results include scoring scores or importance levels.
6. The outbound calling method based on lead operation according to claim 1, characterized in that: Before analyzing and screening the call leads based on the screening rules and / or quantitative models, the method further includes: Obtain an initial quantization model; Extract objective labels from call leads; The initial quantization model is iterated for the first time according to the objective label to obtain a quantization model of the first iteration.
7. The outbound calling method based on lead operation according to claim 4 is characterized in that: After the call lead has experienced a freezing period, before analyzing and screening the call lead based on screening rules and / or quantitative models, the method further includes: The quantization model is iterated for a second time according to the objective labels and the subjective labels to obtain a second-iteration quantization model; wherein the proportion of subjective labels in the label data used to train the quantization model is greater than the proportion of objective labels.
8. An outbound calling device based on clue operation, characterized in that: include: A clue receiving module, used for receiving a call clue and marking the state of the call clue as a pending state; A lead screening module, for analyzing and screening call leads based on screening rules and / or quantitative models; The call issuing module is used to issue the operation instruction to the outbound call system according to the screened call clues, and mark the call clues as issued; wherein the operation instruction includes the call batch and the call cycle; The operation instruction module is used to instruct the outbound call system to perform outbound call operations according to the sending cycle of the call clues.
9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, they are used to implement the outbound calling method based on lead operation as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a server, implements the outbound calling method based on lead operation as described in any one of claims 1-7.