Business demand confirmation method and device and computer equipment
By acquiring and processing historical data from financial clients, and utilizing predictive models and deep learning technologies to automatically determine target groups and business needs, the efficiency and accuracy issues of traditional manual judgment are resolved, enabling fast and accurate personalized services.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-28
- Publication Date
- 2026-04-07
AI Technical Summary
In financial customer service systems, traditional methods rely on customers initiating requests or customer managers making judgments based on their experience. This leads to a contradiction between the limited number of customer managers who can identify customer needs and the large number of customers who require personalized services.
By acquiring historical data information of target users, performing time-series processing and data preprocessing, using predictive sequence models and convolutional neural networks to determine predictive data information, and combining data mining deep learning models, the accuracy of the predicted tags is confirmed with the review end, and target groups are determined based on the predicted tags, and corresponding business requirements are provided.
It can quickly and accurately determine user business needs without human intervention, reducing labor costs and improving the accuracy of business services and user satisfaction.
Smart Images
Figure CN121810296A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus and computer equipment for confirming business requirements. Background Technology
[0002] In financial customer service systems, especially in corporate online banking scenarios, it is usually necessary to differentiate customer access permissions and the services provided in order to better provide personalized business services to different customer groups.
[0003] In order to provide personalized business services to different customers, it is necessary to obtain customer needs in advance. The traditional approach relies on customers to initiate requests or on the manual judgment of account managers. This presents a contradiction between the limited number of account managers who can identify customer needs and the large number of customers who need personalized services. Summary of the Invention
[0004] Therefore, it is necessary to provide a method, apparatus, and computer equipment for quickly and accurately identifying user business needs in order to address the aforementioned technical problems.
[0005] Firstly, this application provides a method for confirming business requirements. The method includes:
[0006] Obtain historical data information of the target user within a preset historical time period;
[0007] Based on historical data, predictive data for target users can be determined.
[0008] Based on historical and forecast data, target groups of target users are determined;
[0009] Based on the target group, determine the business needs of the target users.
[0010] In one embodiment, obtaining historical data information of the target user within a preset historical time period includes:
[0011] The system retrieves initial data information of the target user within a preset historical period from the data source; the initial data information includes basic user attribute information, user transaction information, user relationship information, and external context information.
[0012] The initial data information is processed to obtain historical data information; the historical data information includes user basic attribute sequence, user transaction behavior sequence, relationship network evolution sequence, and external context data sequence.
[0013] In one embodiment, the initial data information is processed to obtain historical data information, including:
[0014] The initial data information is processed to obtain an initial data sequence;
[0015] The initial data sequence is preprocessed to obtain historical data information; the data preprocessing includes at least one of the following: data integration processing, data cleaning processing, and feature extraction processing.
[0016] In one embodiment, the predicted data information of the target user is determined based on historical data information, including:
[0017] Historical data information is sent to each prediction sequence model to obtain the initial prediction data output by each prediction sequence model; wherein, each prediction sequence model outputs one initial prediction data.
[0018] The initial prediction data output by each prediction sequence model is input into the convolutional neural network to obtain the prediction data information of the target user.
[0019] In one embodiment, determining the target group of the target user based on historical data and predicted data includes:
[0020] Historical and predicted data are input into a data mining deep learning model to obtain predicted tags for the target user.
[0021] Send the predicted tags of the target users to the reviewer so that the reviewer can confirm the accuracy of the predicted tags;
[0022] Receive the accuracy results sent by the reviewer;
[0023] If the accuracy result is accurate, the target group of the target user is determined based on the predicted label.
[0024] In one embodiment, determining the target group of a target user based on the predicted tag includes:
[0025] Based on the target user's customer ID, determine the target user's current tags;
[0026] If the predicted label is the same as the current label, the current group of the target user will be used as the target group of the target user.
[0027] If the predicted label is different from the current label, the target group is selected from the candidate groups based on the predicted label and the label information of the candidate groups.
[0028] In one embodiment, the business needs of target users are determined based on target grouping, including:
[0029] Retrieve the list of application services corresponding to the target group;
[0030] Based on the application services included in the application service list, determine the business needs of the target users.
[0031] Secondly, this application also provides a business requirement confirmation device. The device includes:
[0032] The acquisition module is used to acquire historical data information of the target user within a preset historical time period;
[0033] The first determining module is used to determine the predicted data information of the target user based on historical data information;
[0034] The second determination module is used to determine the target group of the target user based on historical data and predicted data.
[0035] The third determination module is used to determine the business needs of target users based on the target group.
[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:
[0037] Obtain historical data information of the target user within a preset historical time period;
[0038] Based on historical data, predictive data for target users can be determined.
[0039] Based on historical and forecast data, target groups of target users are determined;
[0040] Based on the target group, determine the business needs of the target users.
[0041] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:
[0042] Obtain historical data information of the target user within a preset historical time period;
[0043] Based on historical data, predictive data for target users can be determined.
[0044] Based on historical and forecast data, target groups of target users are determined;
[0045] Based on the target group, determine the business needs of the target users.
[0046] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:
[0047] Obtain historical data information of the target user within a preset historical time period;
[0048] Based on historical data, predictive data for target users can be determined.
[0049] Based on historical and forecast data, target groups of target users are determined;
[0050] Based on the target group, determine the business needs of the target users.
[0051] The aforementioned business demand confirmation method, apparatus, and computer equipment acquire historical data information of target users within a preset historical time period. Based on the historical data information, predictive data information of the target users is determined. Based on the historical data information and the predictive data information, target groups of the target users are determined. Based on the target groups, the business demands of the target users are determined. In this application, the historical data information of the target users can be combined to determine the predictive data information, and based on the predictive data information and the historical data information, the target groups of the target users are obtained. Based on the target groups, user demands are determined. Compared with the traditional method of manual experience-based judgment, this application can quickly determine user business demands without human intervention, reducing labor costs. Furthermore, by combining historical data information and predictive data information, the obtained user business demands are more accurate, enabling more precise provision of business services to users and improving user satisfaction. Attached Figure Description
[0052] Figure 1 This is an application environment diagram of the business requirement confirmation method provided in this embodiment;
[0053] Figure 2 A flowchart illustrating the first business requirement confirmation method provided in this embodiment;
[0054] Figure 3 This is a flowchart illustrating the process of obtaining historical data information provided in this embodiment;
[0055] Figure 4 This is a flowchart illustrating the process of determining the predicted data information of the target user provided in this embodiment;
[0056] Figure 5 This is a flowchart illustrating the process of determining the target group of a target user in this embodiment.
[0057] Figure 6 A flowchart illustrating the first business requirement confirmation method provided in this embodiment;
[0058] Figure 7 This is a structural block diagram of a business requirement confirmation device provided in this embodiment;
[0059] Figure 8This is an internal structural diagram of the computer device provided in this embodiment. Detailed Implementation
[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0061] In financial customer service systems, especially in corporate online banking scenarios, it is usually necessary to differentiate customer access permissions and the services provided in order to better provide personalized business services to different customer groups.
[0062] In order to provide personalized business services to different customers, it is necessary to obtain customer needs in advance. The traditional approach relies on customers to initiate requests or on the manual judgment of account managers. This presents a contradiction between the limited number of account managers who can identify customer needs and the large number of customers who need personalized services.
[0063] To address the aforementioned technical problems, the business requirement confirmation method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, when server 102 receives a request from terminal 104 to obtain the business needs of a target user, server 102 obtains the target user's historical data information within a preset historical period. Based on the historical data information, server 102 determines the target user's predicted data information. Based on the historical data information and the predicted data information, server 102 determines the target user's target group. Based on the target group, server 102 determines the target user's business needs.
[0064] The server can be a standalone server or a server cluster. The terminal refers to the user-side terminal device, such as a mobile phone, computer, or other smart terminal.
[0065] In one embodiment, such as Figure 2 As shown, a business requirement confirmation method is provided, which is applied to... Figure 1 Taking the server in the example, the following steps are included:
[0066] S201, Obtain historical data information of the target user within a preset historical time period.
[0067] Target users refer to users who need to confirm business requirements; these can be individual users or enterprise users. Preset historical time periods refer to pre-configured historical time periods, such as the past year, the past month, or the past three months. Historical data information refers to user-related information within the preset historical time periods.
[0068] As an optional implementation of this application, the user identifier of the target user (e.g., company name, company code, etc.) is determined. Based on the user identifier, historical data information of the target user is crawled from the Internet.
[0069] Another optional implementation of this application is to send a data query request for the target user to the query device so that the query device can provide the target user's historical data information within a preset historical period.
[0070] S202, Based on historical data, determine the predicted data information for the target user.
[0071] Among them, predictive data information refers to the related data information of target users in the future time period obtained by predicting target users based on historical data information.
[0072] Optionally, in this embodiment, historical data information is input into a data prediction model, and the data prediction model outputs predicted data information for the target user. The data prediction model is a trained neural network model.
[0073] S203, Based on historical and predicted data, determine the target groups of the target users.
[0074] Among them, the target group refers to the group that the target user is ultimately assigned to.
[0075] As an optional implementation of this application, historical data information and predicted data information are merged to obtain merged data information. Based on the merged data information, the attribute information of the target user is determined. Based on the attribute information of the target user and the attribute information of users in each candidate group, the target group of the target user is determined.
[0076] Another optional implementation of this application is to input historical data information and predicted data information into the user analysis model, output user tags of the target user from the user analysis model, and determine the target group of the target user based on the user tags.
[0077] S204, Based on the target group, determine the business needs of the target users.
[0078] Among them, business requirements refer to the service information needed by the target users.
[0079] As an optional implementation of this application, the business requirement information of other users in the target group besides the target user is determined, and the business requirement information of other users is summarized to obtain the business requirement information summary result. The business requirement information summary result is used as the business requirement of the target user.
[0080] Another optional implementation of this application embodiment is to obtain an application service list corresponding to the target group; wherein, the application service list is pre-configured for the target group; the application service list contains various application services and a service ID corresponding to each application service. Based on the application services included in the application service list, the business needs of the target user are determined. In this embodiment, an optional implementation of determining the business needs of the target user based on the application services included in the application service list is to determine the target service associated with the predicted tag (e.g., financing needs, increasing asset transfer limits, recommending financial products, etc.) from the application services based on the target user's predicted tag, and use the target service as the target user's business needs.
[0081] In this embodiment, historical data information of the target user within a preset historical time period is obtained. Based on the historical data information, predicted data information of the target user is determined. Based on the historical data information and the predicted data information, a target group for the target user is determined. Based on the target group, the business needs of the target user are determined. This application combines the target user's historical data information to determine the predicted data information, and based on the predicted data information and historical data information, obtains the target user's target group. Based on the target group, user needs are determined. Compared to traditional methods of manual experience-based judgment, this application can quickly determine user business needs without human intervention, reducing labor costs. Furthermore, combining historical and predicted data information makes the obtained user business needs more accurate, enabling more precise provision of business services to users and improving user satisfaction.
[0082] In one embodiment, in order to obtain the target user's historical data information more accurately and efficiently, such as Figure 3 As shown, one optional implementation method for obtaining historical data information of a target user within a preset historical time period includes:
[0083] S301: Obtain the initial data information of the target user within a preset historical time period from the data source.
[0084] The initial data information includes basic user attribute information, user transaction information, user relationship information, and external context information.
[0085] Optionally, in this embodiment, the data source can be an enterprise customer information system, a wealth management sales information system, a bank's core system, a financial digital platform, etc.
[0086] Optionally, in this embodiment, the target user's output data information within a preset historical time period is retrieved from the data source based on the target user's user identifier.
[0087] S302, perform time-series processing on the initial data information to obtain historical data information.
[0088] Historical data includes sequences of basic user attributes, sequences of user transaction behaviors, sequences of relationship network evolution, and sequences of external contextual data.
[0089] Optionally, in this embodiment, the initial data information is processed to obtain an initial data sequence. The initial data sequence is then preprocessed to obtain historical data information. This data preprocessing includes at least one of data integration, data cleaning, and feature extraction. An optional implementation of processing the initial data information to obtain the initial data sequence in this embodiment is to add time information to the initial data information based on the time series to obtain historical data information.
[0090] Optionally, in this embodiment, the user's basic attribute sequence includes the company's registered capital, industry, credit rating, etc. (although relatively static, the change history can form a sequence).
[0091] Optionally, in this embodiment, the user transaction behavior sequence includes historical transaction frequency, transaction amount sequence, counterparty change sequence, login behavior sequence, etc.
[0092] Optionally, in this embodiment, the evolution sequence of the relationship network includes changes in the number of upstream and downstream related enterprises, and the time series of the closeness of transactions with the core enterprise.
[0093] Optionally, the external context data sequence in this embodiment includes macroeconomic indicators, industry prosperity index, specific marketing activity cycles, etc.
[0094] In this embodiment, initial data information of the target user within a preset historical time period is obtained from a data source. The initial data information is then processed to obtain an initial data sequence. This initial data sequence is then preprocessed to obtain historical data information; the data preprocessing includes at least one of data integration processing, data cleaning processing, and feature extraction processing. Based on this embodiment, historical data information based on time series can be obtained quickly and accurately.
[0095] In one embodiment, in order to improve the accuracy of the predicted data information, such as Figure 4 As shown, an optional implementation method for determining the predicted data information of the target user based on historical data information includes:
[0096] S401, historical data information is sent to the input of each prediction sequence model to obtain the initial prediction data output by each prediction sequence model.
[0097] Each prediction sequence model outputs an initial prediction data.
[0098] Optionally, in this embodiment, there are various types of prediction sequence models, with priority given to deep learning models such as Long Short-Term Memory (LSTM), Autoregressive Moving Average (ARMA), or Seasonal Autoregressive Integrated Moving Average (SARIMA).
[0099] Optionally, in this embodiment, for each prediction sequence model, historical data information is sent to the prediction sequence model to obtain the initial prediction data output by the prediction sequence model.
[0100] S402, input the initial prediction data output by each prediction sequence model into the convolutional neural network to obtain the prediction data information of the target user.
[0101] Optionally, in this embodiment, the role of the Convolutional Neural Network (CNN) is to assign weights to the output prediction data of each prediction sequence model. Specifically, the CNN weights the output prediction data of each prediction sequence model to obtain the prediction data information of the target user.
[0102] In this embodiment, historical data is sent to each prediction sequence model to obtain initial prediction data output by each model. This initial prediction data is then input into a convolutional neural network to obtain prediction data for the target user. This embodiment effectively improves the accuracy of the obtained prediction data.
[0103] Based on the above embodiments, in order to more accurately determine the target group of the target user, such as Figure 5 As shown, the optional implementation methods for determining target user groups based on historical and predicted data include:
[0104] S501 inputs historical and predicted data into a data mining deep learning model to obtain predicted labels for the target user.
[0105] Optionally, in this embodiment, the predicted label refers to characteristic information used to characterize the target user's business needs.
[0106] For example, predictive labels can be personalized service recommendations (e.g., "recommend supply chain finance products", "suggest increasing transfer limits", "need working capital loans", "have the intention to purchase high-value wealth management products"), dynamic grouping suggestions (e.g., suggest classifying them into the "high-potential value enhancement customer" group or the "potential risk concern" group), intelligent service simplification (e.g., "hide useless menus" or "highlight high-frequency menus"), and demand probability scores (e.g., the probability of financing demand is 85%).
[0107] S502, send the predicted tags of the target user to the reviewer so that the reviewer can confirm the accuracy of the predicted tags.
[0108] The review terminal refers to the terminal device used to review the predicted labels, such as the terminal device of the review expert.
[0109] Optionally, in this embodiment, the predicted tags of the target user are sent to the auditing terminal so that the auditor can confirm the accuracy of the predicted tags through the auditing terminal. The auditor can determine the accuracy of the predicted tags by triggering the selection control on the auditing terminal. For example, by triggering the "confirmation control", the accuracy of the predicted tags is confirmed.
[0110] S503 receives the accuracy result sent by the auditing end.
[0111] S504, if the accuracy result is accurate, determine the target group of the target user based on the predicted label.
[0112] Optionally, in this embodiment, an optional implementation method for determining the target group of a target user based on predicted tags is to determine the target user's current tag based on the target user's customer number. If the predicted tag and the current tag are the same, the target user's current group is taken as the target group. If the predicted tag and the current tag are different, the target group is selected from the candidate groups based on the predicted tag and the tag information of the candidate groups. Here, the customer number refers to the customer document number associated with the target user. In this embodiment, an optional implementation method for determining the target user's current tag based on the target user's customer number is to query whether the customer number has a current tag (the current tag refers to a tag generated in the past and currently in use by the target user). If a current tag exists, it indicates that the target user has previously participated in grouping, i.e., has a current group. In this embodiment, an optional implementation method for selecting the target group from the candidate groups based on the predicted tag and the tag information of the candidate groups is to match the tag information of the predicted tag with the tag information of each candidate group. If a match is successful, the candidate group pointed to by the successfully matched tag information is taken as the target group. If a match fails, a new group is established, and the newly established group is taken as the target group of the target user. The newly established application service list for the group can be determined based on the predicted tags. Specifically, based on the predicted tags, the application services required by the target user are determined, and the required application services are added to the application service list to form the application service list for that group.
[0113] In this embodiment, historical and predicted data are input into a data mining deep learning model to obtain predicted tags for the target user. The predicted tags are then sent to the review panel to confirm their accuracy. The accuracy result is received from the review panel. If the accuracy result is accurate, the target user's target group is determined based on the predicted tags. This embodiment allows for more accurate determination of the target user's target group, enabling the provision of precise and efficient business services to the target user based on the application service list for that target group, thereby improving user satisfaction.
[0114] In one embodiment, such as Figure 6 As shown, an optional implementation of a business requirement confirmation method includes:
[0115] S601, retrieve the initial data information of the target user within a preset historical period from the data source. This initial data information includes basic user attribute information, user transaction information, user relationship information, and external contextual information.
[0116] S602, perform time-series processing on the initial data information to obtain the initial data sequence.
[0117] S603, perform data preprocessing on the initial data sequence to obtain historical data information. Data preprocessing includes at least one of data integration processing, data cleaning processing, and feature extraction processing; historical data information includes user basic attribute sequences, user transaction behavior sequences, relationship network evolution sequences, and external contextual data sequences.
[0118] S604: Historical data information is sent to the input of each prediction sequence model to obtain the initial prediction data output by each prediction sequence model. Each prediction sequence model outputs one initial prediction data.
[0119] S605, input the initial prediction data output by each prediction sequence model into the convolutional neural network to obtain the prediction data information of the target user.
[0120] S606 inputs historical and predicted data into a data mining deep learning model to obtain predicted labels for target users.
[0121] S607, send the predicted tags of the target user to the reviewer so that the reviewer can confirm the accuracy of the predicted tags.
[0122] S608 receives the accuracy result sent by the auditing end.
[0123] S609, if the accuracy result is accurate, determine the current tag of the target user based on the target user's customer number.
[0124] S610: If the predicted label is the same as the current label, the current group of the target user is used as the target group of the target user.
[0125] S611, when the predicted label is different from the current label, select the target group from the candidate groups based on the predicted label and the label information of the candidate groups.
[0126] S612, obtain the list of application services corresponding to the target group.
[0127] S613, Determine the target user's business needs based on the application services included in the application service list.
[0128] This embodiment acquires historical data information of the target user within a preset historical time period. Based on the historical data information, predictive data information of the target user is determined. Based on the historical data information and the predictive data information, the target group of the target user is determined. Based on the target group, the business needs of the target user are determined. In this application, the historical data information of the target user can be combined to determine the predictive data information, and based on the predictive data information and the historical data information, the target group of the target user is obtained. Based on the target group, the user needs are determined. Compared with the traditional method of manual experience judgment, this application can quickly determine the user's business needs without human intervention, reducing labor costs. Furthermore, by combining historical data information and predictive data information, the obtained user business needs are more accurate, enabling more precise provision of business services to users and improving user satisfaction.
[0129] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0130] Based on the same inventive concept, this application also provides a business requirement confirmation apparatus for implementing the business requirement confirmation method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more embodiments of the business requirement confirmation apparatus provided below can be found in the limitations of the business requirement confirmation method described above, and will not be repeated here.
[0131] In one embodiment, such as Figure 7 As shown, a business requirement confirmation device 1 is provided, including: an acquisition module 10, a first determination module 20, a second determination module 30, and a third determination module 40, wherein:
[0132] The acquisition module is used to acquire historical data information of the target user within a preset historical time period;
[0133] The first determining module is used to determine the predicted data information of the target user based on historical data information;
[0134] The second determination module is used to determine the target group of the target user based on historical data and predicted data.
[0135] The third determination module is used to determine the business needs of target users based on the target group.
[0136] In one embodiment, the acquisition module is further configured to: acquire initial data information of the target user within a preset historical period from the data source; wherein the initial data information includes user basic attribute information, user transaction information, user relationship information and external context information;
[0137] The initial data information is processed to obtain historical data information; the historical data information includes user basic attribute sequence, user transaction behavior sequence, relationship network evolution sequence, and external context data sequence.
[0138] In one embodiment, the acquisition module is further specifically used for:
[0139] The initial data information is processed to obtain an initial data sequence;
[0140] The initial data sequence is preprocessed to obtain historical data information; the data preprocessing includes at least one of the following: data integration processing, data cleaning processing, and feature extraction processing.
[0141] In one embodiment, the first determining module is further specifically used for:
[0142] Historical data information is sent to each prediction sequence model to obtain the initial prediction data output by each prediction sequence model; wherein, each prediction sequence model outputs one initial prediction data.
[0143] The initial prediction data output by each prediction sequence model is input into the convolutional neural network to obtain the prediction data information of the target user.
[0144] In one embodiment, the second determining module is further specifically used for:
[0145] Historical and predicted data are input into a data mining deep learning model to obtain predicted tags for the target user.
[0146] Send the predicted tags of the target users to the reviewer so that the reviewer can confirm the accuracy of the predicted tags;
[0147] Receive the accuracy results sent by the reviewer;
[0148] If the accuracy result is accurate, the target group of the target user is determined based on the predicted label.
[0149] In one embodiment, the second determining module is further specifically used for:
[0150] Based on the target user's customer ID, determine the target user's current tags;
[0151] If the predicted label is the same as the current label, the current group of the target user will be used as the target group of the target user.
[0152] If the predicted label is different from the current label, the target group is selected from the candidate groups based on the predicted label and the label information of the candidate groups.
[0153] In one embodiment, the third determining module is further specifically used for:
[0154] Retrieve the list of application services corresponding to the target group;
[0155] Based on the application services included in the application service list, determine the business needs of the target users.
[0156] Each module in the aforementioned business requirement confirmation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.
[0157] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores user tag-related data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a business requirement confirmation method.
[0158] Those skilled in the art will understand that Figure 8The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0159] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:
[0160] Obtain historical data information of the target user within a preset historical time period;
[0161] Based on historical data, predictive data for target users can be determined.
[0162] Based on historical and forecast data, target groups of target users are determined;
[0163] Based on the target group, determine the business needs of the target users.
[0164] In one embodiment, when the processor executes the computer program, it further performs the following steps: acquiring historical data information of the target user within a preset historical time period, including:
[0165] The system retrieves initial data information of the target user within a preset historical period from the data source; the initial data information includes basic user attribute information, user transaction information, user relationship information, and external context information.
[0166] The initial data information is processed to obtain historical data information; the historical data information includes user basic attribute sequence, user transaction behavior sequence, relationship network evolution sequence, and external context data sequence.
[0167] In one embodiment, when the processor executes the computer program, it further performs the following steps: performing time-sequential processing on the initial data information to obtain historical data information, including:
[0168] The initial data information is processed to obtain an initial data sequence;
[0169] The initial data sequence is preprocessed to obtain historical data information; the data preprocessing includes at least one of the following: data integration processing, data cleaning processing, and feature extraction processing.
[0170] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the predicted data information of the target user based on historical data information, including:
[0171] Historical data information is sent to each prediction sequence model to obtain the initial prediction data output by each prediction sequence model; wherein, each prediction sequence model outputs one initial prediction data.
[0172] The initial prediction data output by each prediction sequence model is input into the convolutional neural network to obtain the prediction data information of the target user.
[0173] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining a target group for a target user based on historical data information and predicted data information, including:
[0174] Historical and predicted data are input into a data mining deep learning model to obtain predicted tags for the target user.
[0175] Send the predicted tags of the target users to the reviewer so that the reviewer can confirm the accuracy of the predicted tags;
[0176] Receive the accuracy results sent by the reviewer;
[0177] If the accuracy result is accurate, the target group of the target user is determined based on the predicted label.
[0178] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining a target group of a target user based on the predicted label, including;
[0179] Based on the target user's customer ID, determine the target user's current tags;
[0180] If the predicted label is the same as the current label, the current group of the target user will be used as the target group of the target user.
[0181] If the predicted label is different from the current label, the target group is selected from the candidate groups based on the predicted label and the label information of the candidate groups.
[0182] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the business needs of target users based on target groups, including;
[0183] Retrieve the list of application services corresponding to the target group;
[0184] Based on the application services included in the application service list, determine the business needs of the target users.
[0185] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:
[0186] Obtain historical data information of the target user within a preset historical time period;
[0187] Based on historical data, predictive data for target users can be determined.
[0188] Based on historical and forecast data, target groups of target users are determined;
[0189] Based on the target group, determine the business needs of the target users.
[0190] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: acquiring historical data information of the target user within a preset historical time period, including:
[0191] The system retrieves initial data information of the target user within a preset historical period from the data source; the initial data information includes basic user attribute information, user transaction information, user relationship information, and external context information.
[0192] The initial data information is processed to obtain historical data information; the historical data information includes user basic attribute sequence, user transaction behavior sequence, relationship network evolution sequence, and external context data sequence.
[0193] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: performing time-series processing on the initial data information to obtain historical data information, including:
[0194] The initial data information is processed to obtain an initial data sequence;
[0195] The initial data sequence is preprocessed to obtain historical data information; the data preprocessing includes at least one of the following: data integration processing, data cleaning processing, and feature extraction processing.
[0196] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the predicted data information of the target user based on historical data information, including:
[0197] Historical data information is sent to each prediction sequence model to obtain the initial prediction data output by each prediction sequence model; wherein, each prediction sequence model outputs one initial prediction data.
[0198] The initial prediction data output by each prediction sequence model is input into the convolutional neural network to obtain the prediction data information of the target user.
[0199] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining a target group for a target user based on historical data information and predicted data information, including:
[0200] Historical and predicted data are input into a data mining deep learning model to obtain predicted tags for the target user.
[0201] Send the predicted tags of the target users to the reviewer so that the reviewer can confirm the accuracy of the predicted tags;
[0202] Receive the accuracy results sent by the reviewer;
[0203] If the accuracy result is accurate, the target group of the target user is determined based on the predicted label.
[0204] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining a target group for a target user based on the predicted label, including;
[0205] Based on the target user's customer ID, determine the target user's current tags;
[0206] If the predicted label is the same as the current label, the current group of the target user will be used as the target group of the target user.
[0207] If the predicted label is different from the current label, the target group is selected from the candidate groups based on the predicted label and the label information of the candidate groups.
[0208] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the business needs of target users based on target groups, including;
[0209] Retrieve the list of application services corresponding to the target group;
[0210] Based on the application services included in the application service list, determine the business needs of the target users.
[0211] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:
[0212] Obtain historical data information of the target user within a preset historical time period;
[0213] Based on historical data, predictive data for target users can be determined.
[0214] Based on historical and forecast data, target groups of target users are determined;
[0215] Based on the target group, determine the business needs of the target users.
[0216] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: acquiring historical data information of the target user within a preset historical time period, including:
[0217] The system retrieves initial data information of the target user within a preset historical period from the data source; the initial data information includes basic user attribute information, user transaction information, user relationship information, and external context information.
[0218] The initial data information is processed to obtain historical data information; the historical data information includes user basic attribute sequence, user transaction behavior sequence, relationship network evolution sequence, and external context data sequence.
[0219] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: performing time-series processing on the initial data information to obtain historical data information, including:
[0220] The initial data information is processed to obtain an initial data sequence;
[0221] The initial data sequence is preprocessed to obtain historical data information; the data preprocessing includes at least one of the following: data integration processing, data cleaning processing, and feature extraction processing.
[0222] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the predicted data information of the target user based on historical data information, including:
[0223] Historical data information is sent to each prediction sequence model to obtain the initial prediction data output by each prediction sequence model; wherein, each prediction sequence model outputs one initial prediction data.
[0224] The initial prediction data output by each prediction sequence model is input into the convolutional neural network to obtain the prediction data information of the target user.
[0225] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining a target group for a target user based on historical data information and predicted data information, including:
[0226] Historical and predicted data are input into a data mining deep learning model to obtain predicted tags for the target user.
[0227] Send the predicted tags of the target users to the reviewer so that the reviewer can confirm the accuracy of the predicted tags;
[0228] Receive the accuracy results sent by the reviewer;
[0229] If the accuracy result is accurate, the target group of the target user is determined based on the predicted label.
[0230] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining a target group for a target user based on the predicted label, including;
[0231] Based on the target user's customer ID, determine the target user's current tags;
[0232] If the predicted label is the same as the current label, the current group of the target user will be used as the target group of the target user.
[0233] If the predicted label is different from the current label, the target group is selected from the candidate groups based on the predicted label and the label information of the candidate groups.
[0234] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the business needs of target users based on target groups, including;
[0235] Retrieve the list of application services corresponding to the target group;
[0236] Based on the application services included in the application service list, determine the business needs of the target users.
[0237] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0238] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0239] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for confirming business requirements, characterized in that, The method includes: Obtain historical data information of the target user within a preset historical time period; Based on the historical data, the predicted data information for the target user is determined; Based on the historical data and predicted data, the target group of the target user is determined; Based on the target group, determine the business needs of the target users.
2. The method according to claim 1, characterized in that, The acquisition of historical data information of the target user within a preset historical time period includes: The initial data information of the target user within a preset historical period is obtained from the data source; wherein, the initial data information includes user basic attribute information, user transaction information, user relationship information and external context information; The initial data information is processed in a time series manner to obtain historical data information; wherein, the historical data information includes user basic attribute sequence, user transaction behavior sequence, relationship network evolution sequence, and external context data sequence.
3. The method according to claim 2, characterized in that, The step of performing time-series processing on the initial data information to obtain historical data information includes: The initial data information is processed to obtain an initial data sequence; The initial data sequence is preprocessed to obtain historical data information; wherein the data preprocessing includes at least one of data integration processing, data cleaning processing, and feature extraction processing.
4. The method according to claim 1, characterized in that, The step of determining the predicted data information of the target user based on the historical data information includes: The historical data information is sent to each prediction sequence model to obtain the initial prediction data output by each prediction sequence model; wherein, each prediction sequence model outputs one initial prediction data. The initial prediction data output by each prediction sequence model is input into a convolutional neural network to obtain the prediction data information of the target user.
5. The method according to claim 1, characterized in that, The step of determining the target group of the target user based on the historical data information and the predicted data information includes: The historical data information and the predicted data information are input into a data mining deep learning model to obtain the predicted label of the target user; Send the predicted tags of the target user to the reviewer so that the reviewer can confirm the accuracy of the predicted tags; Receive the accuracy result sent by the auditing terminal; If the accuracy result is accurate, the target group of the target user is determined based on the predicted label.
6. The method according to claim 5, characterized in that, Determining the target group based on the predicted label includes: Based on the target user's customer number, determine the target user's current tag; If the predicted label is the same as the current label, the current group of the target user will be used as the target group of the target user. If the predicted label is different from the current label, the target group is selected from the candidate groups based on the predicted label and the label information of the candidate groups.
7. The method according to claim 1, characterized in that, The step of determining the business needs of the target user based on the target group includes: Obtain the list of application services corresponding to the target group; Based on the application services included in the application service list, determine the business needs of the target user.
8. A business requirement confirmation device, characterized in that, The device includes: The acquisition module is used to acquire historical data information of the target user within a preset historical time period; The first determining module is used to determine the predicted data information of the target user based on the historical data information; The second determining module is used to determine the target group of the target user based on the historical data information and the predicted data information; The third determining module is used to determine the business needs of the target users based on the target group.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the business requirement confirmation method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the business requirement confirmation method according to any one of claims 1 to 7.