Method and apparatus for determining policy, electronic device, and computer program product

Abstract

The application discloses a strategy determination method and device, electronic equipment and computer program product. Relates to the field of financial technology, the method comprises: obtaining the financial data of the target object under the condition that the target object authorizes; obtaining a label identification model, inputting the financial data into the label identification model, and processing to obtain the financial label of the target object, wherein the label identification model classifies the target object based on a target prompt word and financial data to obtain a financial label, the target prompt word at least includes: a model role defining the label identification model, content defining the label identification model, and an output format of the label identification model; determine the outbound call strategy according to the financial label, and execute the outbound call operation on the target object according to the outbound call strategy. Through the present application, the technical problem of low matching accuracy in matching the outbound call strategy for the target object in the related art is solved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and more specifically, to a method, apparatus, electronic device, and computer program product for determining a strategy. Background Technology

[0002] In recent years, merchant acquiring has become an important source of revenue for financial institutions, generating not only transaction income but also driving the growth of comprehensive financial services such as merchant deposits. However, with intensifying market competition and accelerated digital transformation, financial institutions urgently need to improve the efficiency and accuracy of their outreach to merchants and proactively engage them.

[0003] Currently, financial institutions primarily rely on manual operations for merchant management. Staff must periodically log into multiple business systems, manually extracting merchant transaction data, asset information, and other financial data. Based on experience, they assess which merchants exhibit abnormalities such as declining transactions or prolonged periods without transactions, creating lists of "dormant merchants" or "warning merchants," before arranging in-person visits or phone calls. This process depends on individual experience, resulting in low data extraction efficiency, inconsistent data definitions, and delayed action, often intervening only after significant merchant attrition. Furthermore, this method is labor-intensive, has limited coverage, and cannot achieve large-scale, differentiated outreach to a vast number of merchants, hindering precise operations and failing to meet the needs of financial institutions.

[0004] There is currently no effective solution to the technical problem of low matching accuracy when matching outbound calling strategies to target objects in related technologies. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, electronic device, and computer program product for determining a strategy, in order to solve the technical problem of low matching accuracy when matching outbound calling strategies for target objects in related technologies.

[0006] To achieve the above objectives, according to one aspect of this application, a method for determining a strategy is provided. The method includes: acquiring financial data of the target object with its authorization; acquiring a tag recognition model, inputting the financial data into the tag recognition model, and processing it to obtain financial tags for the target object, wherein the tag recognition model classifies the target object based on target prompts and financial data to obtain financial tags, and the target prompts include at least: defining the model role of the tag recognition model, defining the content recognized by the tag recognition model, and defining the output format of the tag recognition model; determining an outbound calling strategy based on the financial tags, and performing an outbound calling operation on the target object according to the outbound calling strategy.

[0007] Optionally, obtaining the financial data of the target object includes: obtaining the transaction information of the target object within a historical time period and obtaining the object information of the target object; preprocessing the transaction information to obtain transaction data, and converting the object information into a format to obtain object data; and the transaction data and object data constitute the financial data.

[0008] Optionally, before inputting financial data into the label recognition model and processing it to obtain the financial label of the target object, the method further includes: receiving a prompt word generation instruction, configuring a target prompt word according to the prompt word generation instruction, and inputting the target prompt word into the label recognition model; inputting financial data into the label recognition model and processing it to obtain the financial label of the target object includes: the label recognition model outputting an initial financial label based on a set of financial data associated with the target prompt word and the target object, and parsing the initial financial label to obtain the financial label of the target object.

[0009] Optionally, determining the outbound calling strategy based on financial tags includes: determining field requirements and strategy type based on the financial tags of the target object, wherein field requirements refer to the fields required when generating an outbound calling strategy; obtaining the strategy database, filtering the strategy database based on the strategy type to obtain the initial outbound calling strategy; configuring the initial outbound calling strategy according to the field requirements to obtain the outbound calling strategy for the target object.

[0010] Optionally, the initial outbound calling strategy is configured according to field requirements. The outbound calling strategy for the target object includes: extracting M sets of outbound calling fields from the data lake based on field requirements, wherein the M sets of outbound calling fields include at least: fixed fields and user feature fields, and M is a positive integer; converting the format of the M sets of outbound calling fields to obtain M sets of converted outbound calling fields, and concatenating the M sets of converted outbound calling fields to obtain the processed outbound calling fields; obtaining the object data of the target object, and filling the processed outbound calling fields and object data into the initial outbound calling strategy to obtain the outbound calling strategy.

[0011] Optionally, performing an outbound call operation on the target object according to the outbound call strategy includes: obtaining the outbound call preference type of the target object, wherein the outbound call preference type includes at least one of the following: device outbound call type and manual outbound call type; if the outbound call preference type of the target object is device outbound call type, uploading the outbound call strategy of the target object to the outbound call system, wherein when the outbound call system receives the outbound call strategy, it performs an outbound call operation on the target object according to the outbound call strategy; if the outbound call preference type is manual outbound call type, obtaining the target client, sending the outbound call strategy of the target object to the target client, wherein the target client refers to a client that is in an idle state selected from multiple candidate clients, and the target client performs an outbound call operation on the target object according to the outbound call strategy.

[0012] Optionally, after performing an outbound call operation on the target object according to the outbound call strategy, the method further includes: obtaining the outbound call result of the target object, wherein the outbound call result refers to the result of the target object performing financial behavior based on the outbound call strategy; adjusting the financial label of the target object according to the outbound call result to obtain the adjusted financial label, and adjusting the outbound call strategy of the target object according to the adjusted financial label.

[0013] To achieve the above objectives, according to another aspect of this application, a strategy determination apparatus is provided. The apparatus includes: a first acquisition unit, configured to acquire financial data of a target object upon authorization; a second acquisition unit, configured to acquire a tag recognition model, input the financial data into the tag recognition model, and process it to obtain financial tags for the target object, wherein the tag recognition model classifies the target object based on target prompts and financial data to obtain financial tags, and the target prompts include at least: defining the model role of the tag recognition model, defining the content recognized by the tag recognition model, and defining the output format of the tag recognition model; and a determination unit, configured to determine an outbound calling strategy based on the financial tags, and perform an outbound calling operation on the target object according to the outbound calling strategy.

[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein the method for determining the execution of any of the above-described strategies by the device where the computer-readable storage medium is located is provided when the executable program is running.

[0015] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory storing an executable program, and the processor for running the program, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the determination method of any of the above strategies.

[0016] According to another aspect of the present invention, a computer program product is also provided, the computer program product including a computer program, wherein the computer program, when executed by a processor, implements the determination method of any of the above strategies.

[0017] In this embodiment, a strategy is determined by acquiring the financial data of the target object with its authorization; a tag recognition model is then acquired, and the financial data is input into the tag recognition model to obtain the financial tags of the target object. The tag recognition model categorizes the target object based on target prompts and financial data to obtain financial tags. The target prompts include at least: defining the model role of the tag recognition model, defining the content recognized by the tag recognition model, and defining the output format of the tag recognition model; an outbound calling strategy is determined based on the financial tags, and an outbound calling operation is performed on the target object according to the outbound calling strategy. This solves the technical problem of low matching accuracy when matching outbound calling strategies for target objects in related technologies. By inputting the financial data of the target object into the tag recognition model, processing it to obtain the financial tags of the target object, determining the outbound calling strategy based on the financial tags, and performing an outbound calling operation on the target object according to the outbound calling strategy, the technical effect of improving the accuracy of matching outbound calling strategies for target objects is achieved. Attached Figure Description

[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 It is a hardware structure block diagram of a computer terminal (or mobile device) used to implement a method for determining a strategy;

[0020] Figure 2 This is a flowchart of a strategy determination method provided according to an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of a method for determining an optional strategy according to an embodiment of this application;

[0022] Figure 4 This is a schematic diagram of a strategy determination device provided according to an embodiment of this application;

[0023] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties. For example, this system has interfaces with relevant users or organizations to provide users with corresponding operation data for them to choose to agree to or refuse automated decision-making results. Before obtaining relevant information, a request for obtaining the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained after receiving consent from the aforementioned user or organization; if the user chooses to refuse, the expert decision-making process is initiated. Users can view the purpose of data use in real time through authorization decoding and have the right to withdraw authorization or delete data at any time. After the authorization is withdrawn, the system will terminate the relevant data processing within 24 hours.

[0027] It should be noted that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize use or refuse use.

[0028] Example 1

[0029] According to an embodiment of this application, a method embodiment for determining a strategy is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1This is a hardware structure block diagram of a computer terminal (or mobile device) used to implement a method for determining a strategy, such as... Figure 1 As shown, computer terminal 10 (or mobile device) may include one or more ( Figure 1 The processor 102 (which may include, but is not limited to, a microprocessor MCU (Microcontroller Unit) or a programmable gate array (FPGA)) is shown as 102a, 102b, ..., 102n. It also includes a memory 104 for storing data and a transmission device 106 for communication functions. In addition, it may include: a display, an input / output interface, a Universal Serial Bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a keyboard, a cursor control device, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0031] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0032] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the strategy determination method in the embodiments of this application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the aforementioned strategy determination method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0033] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network interface controller (NIC) and a network interface, which can be connected to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a radio frequency (RF) module, used for wireless communication with the Internet.

[0034] The display can be, for example, a touchscreen liquid crystal display (LCD), which allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0035] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for determining the strategy shown. Figure 2 This is a flowchart of a strategy determination method provided according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0036] Step S201: With the authorization of the target object, obtain the target object's financial data.

[0037] It should be noted that the target can refer to merchants who have opened financial services with financial institutions, such as individual merchants or corporate merchants. In order to send financial products that match individual characteristics to the above-mentioned target, after obtaining the list of targets, the authorization status of each target is first queried. After the authorization status indicates that the relevant data can be obtained, the financial data of the above-mentioned target is obtained from different systems or databases through the application programming interface. If the target does not allow the relevant data to be obtained, the data collection operation is not triggered.

[0038] It should be noted that financial data can refer to merchant information stored internally by financial institutions. This may include merchant profile information (such as merchant identifiers like ID numbers and merchant entity types), transaction data (such as the number of transactions and transaction amounts), and the target entity's financial information within the financial institution (such as deposits). When acquiring this financial data, the raw data can be preprocessed to generate standardized descriptions that the model can input, thus obtaining the financial data.

[0039] Step S202: Obtain the label recognition model. Input the financial data into the label recognition model and process it to obtain the financial label of the target object. The label recognition model classifies the target object based on the target prompt words and financial data to obtain the financial label. The target prompt words include at least: defining the model role of the label recognition model, defining the content recognized by the label recognition model, and defining the output format of the label recognition model.

[0040] It should be noted that the label recognition model can refer to a trained Large Language Model (LLM). After obtaining the financial data of the target object, this data can be input into the label recognition model. The target prompt words guide the label recognition model to process and obtain the classification result of the target object, that is, to obtain the financial label of the target object. Here, the target prompt words are prompt templates with a complete instruction structure, and their content includes three legal elements: defining the model role, defining the recognition content, and defining the output format.

[0041] It should be noted that financial tags can include: dormant merchant tags, newly added merchant tags, and warning merchant tags. Dormant merchant tags can include: new dormant merchants, lightly dormant merchants, and deeply dormant merchants; newly added merchant tags can include: existing merchants and newly added merchants; warning merchant tags can include: newly acquired warning merchants, and existing merchants with low, medium, and high warning levels. When the above tag recognition model classifies target objects, financial data can be concatenated with target prompts to form a complete input. Then, semantic reasoning is performed based on the complete input to output a structured and standardized set of merchant classification identifiers, i.e., the financial tags.

[0042] Step S203: Determine the outbound calling strategy based on the financial label, and perform outbound calling operations on the target object according to the outbound calling strategy.

[0043] Specifically, after obtaining the financial tags output by the aforementioned model, outbound calling strategies related to the target can be matched based on the financial tags and the target's communication history. For example, the outbound calling strategy could be: "Outbound calling time: weekdays 10:00–16:00, key points of the message: inquiring about system problems, level of interest: medium to high, follow-up action: on-site service." Finally, outbound calls are made to the target based on the determined outbound calling strategy.

[0044] The strategy determination method provided in this application embodiment obtains the financial data of the target object with the target object's authorization; obtains a tag recognition model, inputs the financial data into the tag recognition model, and processes it to obtain the financial tags of the target object. The tag recognition model classifies the target object based on target prompts and financial data to obtain financial tags. The target prompts include at least: defining the model role of the tag recognition model, defining the content recognized by the tag recognition model, and defining the output format of the tag recognition model; determining an outbound calling strategy based on the financial tags, and performing an outbound calling operation on the target object according to the outbound calling strategy. This solves the technical problem of low matching accuracy when matching outbound calling strategies for target objects in related technologies. By inputting the financial data of the target object into the tag recognition model, processing it to obtain the financial tags of the target object, determining the outbound calling strategy based on the financial tags, and performing an outbound calling operation on the target object according to the outbound calling strategy, the technical effect of improving the accuracy of matching outbound calling strategies for target objects is achieved.

[0045] Optionally, in the strategy determination method provided in this application embodiment, obtaining the financial data of the target object includes: obtaining the transaction information of the target object within a historical time period, and obtaining the object information of the target object; preprocessing the transaction information to obtain transaction data, and converting the object information into a format to obtain object data; and the transaction data and object data constitute financial data.

[0046] Specifically, in order to obtain the financial data of the target object, one can first obtain the target object's object information and transaction information within a historical time period. Transaction information refers to the target object's transaction flow records, including: transaction time, transaction amount, etc.; object information refers to the static attribute data of the target object stored by the financial institution, including: merchant number, merchant type, industry, etc. Transaction data can reflect the target object's operating status, while object data can reflect the target object's static basic attributes.

[0047] Furthermore, after obtaining the aforementioned object and transaction information, the transaction information can be cleaned (e.g., outlier removal), aggregated by time period, and standardized to transform it into a semantic summary that the model can understand, thus obtaining transaction data. Simultaneously, the object information is formatted into natural language text format suitable for model input, yielding object data. Finally, the transaction data and object data are combined to form the complete semantic input text used to input the label recognition model, i.e., obtaining financial data.

[0048] This embodiment processes the information associated with the target object to obtain financial data, enabling subsequent large models to perform accurate classification based on the complete merchant context, rather than relying solely on isolated numerical values, thereby improving the accuracy of financial tag generation and the depth of semantic understanding.

[0049] Optionally, in the strategy determination method provided in the embodiments of this application, before inputting financial data into the label recognition model and processing it to obtain the financial label of the target object, the method further includes: receiving a prompt word generation instruction, configuring a target prompt word according to the prompt word generation instruction, and inputting the target prompt word into the label recognition model; inputting financial data into the label recognition model and processing it to obtain the financial label of the target object includes: the label recognition model outputting an initial financial label based on a set of financial data associated with the target prompt word and the target object, and parsing the initial financial label to obtain the financial label of the target object.

[0050] Specifically, after obtaining the financial data of the target object, in order to accurately output the financial tags of the target object using the tag recognition model, a prompt word generation instruction to trigger the tag recognition task can first be received. Although this instruction does not contain specific rules, it can indicate the business intent. Therefore, target prompt words can be configured based on this instruction. For example, the generated target prompt words consist of three parts: model role definition: such as "You are a profile analyst"; recognition content definition: such as "Determine whether it belongs to a dormant merchant: no transactions in the past 3 months"; and output format definition: such as "output in a preset format". The configured target prompt words are then input into the tag recognition model.

[0051] Furthermore, during operation, the label recognition model can perform semantic reasoning and classification on the input financial data based on target prompts, directly outputting unverified initial financial labels. Since these initial financial labels are prone to format errors and semantic ambiguity, they can be parsed—that is, standardized cleaning, format verification, and semantic normalization—to obtain the final structured labels that can be directly used, i.e., the financial labels of the target object.

[0052] This embodiment outputs financial tags based on target prompt words using a tag recognition model, which can significantly reduce operation and maintenance costs and improve response speed.

[0053] Optionally, in the strategy determination method provided in this application embodiment, determining the outbound call strategy based on the financial tag includes: determining the field requirements and strategy type based on the financial tag of the target object, wherein the field requirements refer to the fields required when generating an outbound call strategy; obtaining the strategy database, filtering the strategy database based on the strategy type to obtain the initial outbound call strategy; configuring the initial outbound call strategy according to the field requirements to obtain the outbound call strategy of the target object.

[0054] Specifically, after obtaining the financial tags output by the tag recognition model, in order to determine the outbound calling strategy to match the target object, the outbound calling scenario can first be classified according to the output financial tags, thereby obtaining the strategy type and the fields required to generate the outbound calling strategy (i.e., field requirements). Among them, the strategy type can represent the outbound calling intent, such as waking up dormant merchants or guiding new merchants.

[0055] Furthermore, a strategy database storing multiple outbound calling strategies can be obtained. Each outbound calling strategy in this database corresponds to a different strategy record, and each strategy record can include a strategy number, strategy type, and subsequent actions. At this point, based on the strategy type determined by the aforementioned financial tags, all matching strategy records of that type can be batch-queried from the strategy database, and sorted by dimensions such as effective time, priority, and branch region. The most matching strategy is then selected as the initial outbound calling strategy. Then, based on the data listed in the field requirements, the reserved variable placeholders in the initial outbound calling strategy are filled in, thereby generating the outbound calling strategy.

[0056] This embodiment improves the efficiency of strategy generation by determining the outbound calling strategy that matches the target object based on financial tags, which lays the foundation for the successful execution of subsequent outbound calling strategies.

[0057] Optionally, in the strategy determination method provided in this application embodiment, configuring the initial outbound call strategy according to field requirements to obtain the outbound call strategy for the target object includes: extracting M sets of outbound call fields from the data lake based on field requirements, wherein the M sets of outbound call fields include at least: fixed fields and user feature fields, and M is a positive integer; converting the format of the M sets of outbound call fields to obtain M sets of converted outbound call fields, and concatenating the M sets of converted outbound call fields to obtain processed outbound call fields; obtaining the object data of the target object, and filling the processed outbound call fields and object data into the initial outbound call strategy to obtain the outbound call strategy.

[0058] Specifically, after obtaining the initial outbound calling strategy based on strategy type filtering, multiple sets of outbound calling fields are first retrieved from the data lake associated with financial institutions based on the field requirements determined by financial tags. Among these, fixed fields refer to basic information that must be included in every outbound call, while user characteristic fields are fields determined based on the object's status. These outbound calling fields are then formatted and converted into natural language expressions, resulting in multiple sets of converted outbound calling fields. Finally, the converted outbound calling fields are combined into a coherent string according to semantic order to obtain the processed outbound calling fields.

[0059] Furthermore, after obtaining the object data associated with the target object after format conversion, the processed outbound call fields and object data are filled into the placeholders of the initial outbound call strategy to obtain the outbound call strategy, which can significantly improve the trust level of the target object.

[0060] This embodiment achieves personalized generation of outbound calling strategies through the process of on-demand data retrieval, format conversion, and splicing, solving the problems of empty content and lack of data support in traditional outbound calling. It ensures that each outbound calling instruction is based on accurate behavioral and identity information, improving the accuracy and effectiveness of outbound calls.

[0061] Optionally, in the strategy determination method provided in this application embodiment, performing an outbound call operation on the target object according to the outbound call strategy includes: obtaining the outbound call preference type of the target object, wherein the outbound call preference type includes at least one of the following: device outbound call type and manual outbound call type; when the outbound call preference type of the target object is device outbound call type, uploading the outbound call strategy of the target object to the outbound call system, wherein when the outbound call system receives the outbound call strategy, performing an outbound call operation on the target object according to the outbound call strategy; when the outbound call preference type is manual outbound call type, obtaining the target client, sending the outbound call strategy of the target object to the target client, wherein the target client refers to a client that is in an idle state selected from multiple candidate clients, and the target client performs an outbound call operation on the target object according to the outbound call strategy.

[0062] Specifically, after obtaining the outbound calling strategy for the target audience, the system first retrieves the outbound calling preference types stored by financial institutions, determined based on the target audience's historical behavior. Among these preference types, device-based outbound calling refers to calls made automatically by the outbound calling system, suitable for merchants with abnormal transaction data but no obvious emotional feedback, such as dormant merchants with long-term inactivity. Human-based outbound calling refers to calls made after specific suggestions have been offered or services have been provided to high-value, high-quality merchants. By differentiating merchants' communication preferences, outbound calling resources are allocated rationally, avoiding interference with merchants who are not suited to automated outbound calling.

[0063] When the target audience's outbound calling preference type is device-based, the defined outbound calling strategy can be uploaded to the outbound calling system. The system then performs the outbound calls according to the strategy, achieving batch outreach without human intervention, improving efficiency, and reducing labor costs. When the outbound calling preference type is manual outbound calling, candidate clients of financial institution outbound callers can be obtained. Idle clients are then selected to obtain the target clients. Finally, the target audience's outbound calling strategy is sent to the target clients, and the outbound callers using those clients perform the manual outbound calls.

[0064] This embodiment distinguishes between intelligent outbound calling and human outbound calling based on outbound calling preference type, and pushes outbound calling strategies to the outbound calling system or idle terminals respectively. This achieves intelligent distribution of outbound calling tasks and reasonable allocation of resources, which not only improves the efficiency of automated outbound calling, but also ensures that high-value or highly sensitive merchants can receive human service. It avoids the decline in customer experience or waste of resources caused by "one-size-fits-all" outbound calling, making the entire outbound calling process more practical, efficient and implementable.

[0065] Optionally, in the strategy determination method provided in the embodiments of this application, after performing outbound call operation on the target object according to the outbound call strategy, the method further includes: obtaining the outbound call result of the target object, wherein the outbound call result refers to the result of the target object performing financial behavior based on the outbound call strategy; adjusting the financial tag of the target object according to the outbound call result to obtain the adjusted financial tag, and adjusting the outbound call strategy of the target object according to the adjusted financial tag.

[0066] Specifically, after performing an outbound call on the target, the outbound call result can be obtained first, that is, the actual subsequent actions related to financial business that the target took after receiving the outbound call, including: resuming the transaction, making service suggestions, or no response. Then, the effectiveness of the outbound call can be judged based on the actual feedback, so that subsequent actions are supported by real data.

[0067] Furthermore, since financial tags can identify the transaction activity status of a target, the target's current financial tag can be updated based on the outbound call results to obtain an adjusted financial tag. For example, if the target resumes transactions after the outbound call, the original "dormant merchant" tag is changed to "active merchant"; if the merchant explicitly states that they will not use the service, it is changed to "churned merchant". Finally, the content and method of the next stage of outbound calls are regenerated based on the adjusted financial tag, that is, the outbound call strategy for the target is adjusted, such as stopping wake-up calls for "active merchants".

[0068] This embodiment updates the financial tag of the target object by collecting actual behavioral feedback, and adjusts the subsequent outbound calling strategy accordingly, thereby reducing invalid outbound calls, improving resource utilization efficiency, and increasing the merchant wake-up success rate.

[0069] This application also provides an optional method for determining a strategy. Figure 3 This is a schematic diagram of an optional strategy determination method provided according to an embodiment of this application, such as... Figure 3 As shown, the method includes:

[0070] First, a data acquisition module configured by the financial institution can retrieve financial data for all objects from the data lake associated with the institution, thus obtaining an object list. Each object in the object list is associated with a set of financial data, and each set of financial data can include transaction data and object data. Then, the object list is input into a label recognition model trained by a large model. The label recognition model classifies each object in the object list based on the target prompt words configured according to the prompt word generation instructions, thereby outputting a financial label for each object.

[0071] Furthermore, after obtaining the financial tag for each object in the object list, a matching outbound calling strategy can be selected from the strategy database based on this financial tag. Different outbound calling strategies are then assigned to the outbound calling system or the client of the financial institution's outbound callers based on each object's outbound calling preference type. For example, if the target object's outbound calling preference type is device-based, the determined outbound calling strategy can be uploaded to the outbound calling system, which then performs the outbound calling operation according to the strategy, achieving batch outreach without human intervention, improving efficiency, and reducing labor costs. If the outbound calling preference type is manual outbound calling, candidate clients of the financial institution's outbound callers can be obtained, and then idle clients can be selected to obtain the target client. Finally, the outbound calling strategy for the target object is sent to the target client, and the outbound caller using the target client performs the manual outbound calling operation.

[0072] Furthermore, after performing outbound calls on all targets, the system first obtains the outbound call results for each target. This means acquiring the actual subsequent financial transactions that each target engaged in after receiving the call, including: resuming transactions, explicitly stating they will no longer use the service, offering service suggestions, or showing no response. The effectiveness of the outbound call is then determined based on the actual feedback, ensuring that subsequent actions are supported by real data. The system then updates each target's current financial label based on these results, resulting in an adjusted financial label. For example, if a target resumes transactions after the outbound call, the original "dormant merchant" label is changed to "active merchant"; if a merchant explicitly states they will no longer use the service, it is changed to "churned merchant." Finally, the system regenerates the content and method of the next stage of outbound calls based on the adjusted financial labels, thus adjusting the outbound call strategy for each target, such as ceasing wake-up calls for "active merchants."

[0073] This embodiment improves the accuracy of matching outbound calling strategies to target objects by inputting the financial data of the target object into a tag recognition model, processing it to obtain the target object's financial tag, determining the outbound calling strategy based on the financial tag, and then performing the outbound calling operation on the target object according to the outbound calling strategy.

[0074] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0075] Example 2

[0076] This application also provides a strategy determination apparatus. It should be noted that the strategy determination apparatus of this application can be used to execute the strategy determination method provided in this application. The strategy determination apparatus provided in this application will be described below.

[0077] According to an embodiment of this application, an apparatus for determining the method for implementing the above-described strategy is also provided. Figure 4 This is a schematic diagram of a strategy determination device provided according to an embodiment of this application, such as... Figure 4 As shown, the device includes: a first acquisition unit 40, a second acquisition unit 41, and a determination unit 42.

[0078] The first acquisition unit 40 is used to acquire the financial data of the target object when the target object authorizes it.

[0079] The second acquisition unit 41 is used to acquire the label recognition model, input financial data into the label recognition model, process it to obtain the financial label of the target object, wherein the label recognition model classifies the target object based on the target prompt words and financial data to obtain the financial label, and the target prompt words include at least: defining the model role of the label recognition model, defining the content recognized by the label recognition model, and the output format of the label recognition model;

[0080] The determining unit 42 is used to determine the outbound calling strategy based on the financial tag, and to perform outbound calling operations on the target object according to the outbound calling strategy.

[0081] The strategy determination device provided in this application embodiment acquires the financial data of the target object by a first acquisition unit 40 under the authorization of the target object; a second acquisition unit 41 acquires a tag recognition model, inputs the financial data into the tag recognition model, and processes it to obtain the financial tag of the target object. The tag recognition model classifies the target object based on target prompts and financial data to obtain the financial tag. The target prompts include at least: defining the model role of the tag recognition model, defining the content recognized by the tag recognition model, and defining the output format of the tag recognition model; the determination unit 42 determines the outbound calling strategy based on the financial tag and performs an outbound calling operation on the target object according to the outbound calling strategy. This solves the technical problem of low matching accuracy when matching outbound calling strategies for target objects in related technologies. By inputting the financial data of the target object into the tag recognition model, processing it to obtain the financial tag of the target object, determining the outbound calling strategy based on the financial tag, and performing an outbound calling operation on the target object according to the outbound calling strategy, the technical effect of improving the accuracy of matching outbound calling strategies for target objects is achieved.

[0082] Optionally, in the strategy determination device provided in the embodiments of this application, the first acquisition unit 40 includes: a first acquisition module, used to acquire transaction information of the target object within a historical time period and acquire object information of the target object; a processing module, used to preprocess the transaction information to obtain transaction data and convert the object information into a format to obtain object data; and a composition module, used to compose financial data from the transaction data and the object data.

[0083] Optionally, in the strategy determination apparatus provided in the embodiments of this application, the apparatus further includes: a receiving unit, configured to receive a prompt word generation instruction before inputting financial data into the label recognition model and processing it to obtain the financial label of the target object, configure a target prompt word according to the prompt word generation instruction, and input the target prompt word into the label recognition model; the apparatus further includes: an output module, configured to have the label recognition model output an initial financial label based on a set of financial data associated with the target prompt word and the target object, and to parse the initial financial label to obtain the financial label of the target object.

[0084] Optionally, in the strategy determination device provided in this application embodiment, the determination unit 42 includes: a determination module, used to determine field requirements and strategy type based on the financial tag of the target object, wherein the field requirements refer to the fields required when generating an outbound call strategy; a second acquisition module, used to acquire a strategy database and filter the initial outbound call strategy from the strategy database based on the strategy type; and a configuration module, used to configure the initial outbound call strategy according to the field requirements to obtain the outbound call strategy of the target object.

[0085] Optionally, in the strategy determination device provided in this application embodiment, the determination unit 42 includes: an extraction module, used to extract M sets of outbound call fields from the data lake based on field requirements, wherein the M sets of outbound call fields include at least: fixed fields and user feature fields, and M is a positive integer; a conversion module, used to convert the format of the M sets of outbound call fields to obtain M sets of converted outbound call fields, and to concatenate the M sets of converted outbound call fields to obtain processed outbound call fields; and a third acquisition module, used to acquire object data of the target object, and to fill the processed outbound call fields and object data into the initial outbound call strategy to obtain the outbound call strategy.

[0086] Optionally, in the strategy determination device provided in this application embodiment, the determination unit 42 includes: a fourth acquisition module, used to acquire the outbound call preference type of the target object, wherein the outbound call preference type includes at least one of the following: device outbound call type and manual outbound call type; an upload module, used to upload the outbound call strategy of the target object to the outbound call system when the outbound call preference type of the target object is device outbound call type, wherein when the outbound call system receives the outbound call strategy, it performs an outbound call operation on the target object according to the outbound call strategy; the fourth acquisition module, used to acquire the target client when the outbound call preference type is manual outbound call type, and send the outbound call strategy of the target object to the target client, wherein the target client refers to a client that is in an idle state selected from multiple candidate clients, and the target client performs an outbound call operation on the target object according to the outbound call strategy.

[0087] Optionally, in the strategy determination device provided in the embodiments of this application, the device further includes: a third acquisition unit, configured to acquire the outbound call result of the target object after performing an outbound call operation on the target object according to the outbound call strategy, wherein the outbound call result refers to the result after the target object performs financial behavior based on the outbound call strategy; and an adjustment unit, configured to adjust the financial tag of the target object according to the outbound call result to obtain the adjusted financial tag, and adjust the outbound call strategy of the target object according to the adjusted financial tag.

[0088] It should be noted that the first acquisition unit 40, the second acquisition unit 41, and the determination unit 42 mentioned above correspond to steps S201 to S203 in Embodiment 1. The instances and application scenarios implemented by the above units and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and can run in the computer terminal 10 provided in Embodiment 1.

[0089] Example 3

[0090] Embodiments of this application may provide a computer terminal, which may be any computer terminal device in a group of computer terminals. Optionally, in this embodiment, the aforementioned computer terminal may also be replaced with a mobile terminal or an electronic device, etc.

[0091] Optionally, in this embodiment, the computer terminal may be located in at least one of a plurality of network devices in a computer network.

[0092] In this embodiment, the computer terminal described above can execute the program code for the following steps in the strategy determination method: With authorization from the target object, acquire the target object's financial data; acquire a tag recognition model, input the financial data into the tag recognition model, and process it to obtain the target object's financial tags, wherein the tag recognition model classifies the target object based on target prompts and financial data to obtain financial tags, and the target prompts include at least: defining the model role of the tag recognition model, defining the content recognized by the tag recognition model, and defining the output format of the tag recognition model; determine the outbound calling strategy based on the financial tags, and perform outbound calling operations on the target object according to the outbound calling strategy.

[0093] Optionally, the computer terminal described above can execute the program code for the following steps in the strategy determination method: obtaining transaction information of the target object within a historical time period and obtaining object information of the target object; preprocessing the transaction information to obtain transaction data and converting the object information into a format to obtain object data; and constructing financial data from the transaction data and object data.

[0094] Optionally, the computer terminal described above can execute the program code for the following steps in the strategy determination method: receiving a prompt word generation instruction, configuring a target prompt word according to the prompt word generation instruction, and inputting the target prompt word into a label recognition model; inputting financial data into the label recognition model and processing it to obtain the financial label of the target object includes: the label recognition model outputting an initial financial label based on a set of financial data associated with the target prompt word and the target object, and parsing the initial financial label to obtain the financial label of the target object.

[0095] Optionally, the computer terminal described above can execute the program code for the following steps in the strategy determination method: determining field requirements and strategy type based on the financial tags of the target object, wherein field requirements refer to the fields required when generating an outbound call strategy; obtaining the strategy database, and filtering the strategy database based on the strategy type to obtain the initial outbound call strategy; configuring the initial outbound call strategy according to the field requirements to obtain the outbound call strategy for the target object.

[0096] Optionally, the computer terminal described above can execute the following steps in the strategy determination method: extracting M sets of outbound call fields from the data lake based on field requirements, wherein the M sets of outbound call fields include at least: fixed fields and user characteristic fields, and M is a positive integer; converting the format of the M sets of outbound call fields to obtain M sets of converted outbound call fields, and concatenating the M sets of converted outbound call fields to obtain processed outbound call fields; obtaining the object data of the target object, and filling the processed outbound call fields and object data into the initial outbound call strategy to obtain the outbound call strategy.

[0097] Optionally, the computer terminal described above may execute the following steps in the strategy determination method: obtaining the outbound call preference type of the target object, wherein the outbound call preference type includes at least one of the following: device outbound call type and manual outbound call type; if the outbound call preference type of the target object is device outbound call type, uploading the outbound call strategy of the target object to the outbound call system, wherein when the outbound call system receives the outbound call strategy, it performs an outbound call operation on the target object according to the outbound call strategy; if the outbound call preference type is manual outbound call type, obtaining the target client, sending the outbound call strategy of the target object to the target client, wherein the target client refers to a client that is in an idle state selected from multiple candidate clients, and the target client performs an outbound call operation on the target object according to the outbound call strategy.

[0098] Optionally, the computer terminal described above may execute the following steps in the method for determining the strategy: obtaining the outbound call result of the target object, wherein the outbound call result refers to the result of the target object performing financial behavior based on the outbound call strategy; adjusting the financial label of the target object according to the outbound call result to obtain the adjusted financial label, and adjusting the outbound call strategy of the target object according to the adjusted financial label.

[0099] Optionally, Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (Only one is shown) processor 502, memory 504, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0100] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the strategy determination method and apparatus in this application embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the aforementioned strategy determination method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0101] The processor can invoke the information and application programs stored in the memory through the transmission device to execute the steps described above in the method for determining the strategy.

[0102] Those skilled in the art will understand that Figure 5 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 5 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 5 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 5 The different configurations shown.

[0103] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0104] Example 4

[0105] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the strategy determination method provided in Embodiment 1.

[0106] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0107] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: obtaining financial data of the target object when authorized by the target object; obtaining a tag recognition model, inputting the financial data into the tag recognition model, and processing it to obtain financial tags of the target object, wherein the tag recognition model classifies the target object based on target prompts and financial data to obtain financial tags, and the target prompts include at least: defining the model role of the tag recognition model, defining the content recognized by the tag recognition model, and defining the output format of the tag recognition model; determining an outbound calling strategy based on the financial tags, and performing an outbound calling operation on the target object according to the outbound calling strategy.

[0108] This application also provides a computer program product that, when executed on a data processing device, is suitable for performing steps of a strategy determination method.

[0109] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0110] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0112] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0113] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0114] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0115] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for determining a strategy, characterized in that, include: With the authorization of the target object, obtain the financial data of the target object; A tag recognition model is obtained by inputting financial data into the tag recognition model and processing it to obtain the financial tags of the target object. The tag recognition model classifies the target object based on target prompts and the financial data to obtain the financial tags. The target prompts include at least: defining the model role of the tag recognition model, defining the content recognized by the tag recognition model, and defining the output format of the tag recognition model. The outbound calling strategy is determined based on the financial label, and the outbound calling operation is performed on the target object according to the outbound calling strategy.

2. The method according to claim 1, characterized in that, Obtaining the financial data of the target object includes: Obtain transaction information of the target object within a historical time period, and obtain object information of the target object; The transaction information is preprocessed to obtain transaction data, and the object information is format-converted to obtain object data; The financial data is composed of the transaction data and the object data.

3. The method according to claim 1, characterized in that, Before inputting financial data into the label recognition model and processing it to obtain the financial label of the target object, the method further includes: Receive prompt word generation instructions, configure the target prompt word according to the prompt word generation instructions, and input the target prompt word into the label recognition model; Financial data is input into a label recognition model, and the financial labels of the target object are obtained by processing the data, including: The tag recognition model outputs an initial financial tag based on the target prompt word and a set of financial data associated with the target object, and then parses the initial financial tag to obtain the financial tag of the target object.

4. The method according to claim 1, characterized in that, Determining outbound calling strategies based on the aforementioned financial tags includes: The field requirements and strategy type are determined based on the financial tags of the target object, wherein the field requirements refer to the fields required when generating an outbound call strategy; Obtain the strategy database, and filter the initial outbound call strategy from the strategy database based on the strategy type; Configure the initial outbound call strategy according to the field requirements to obtain the outbound call strategy for the target object.

5. The method according to claim 4, characterized in that, Configure the initial outbound call strategy according to the field requirements to obtain the outbound call strategy for the target object, including: Based on the aforementioned field requirements, M sets of outbound calling fields are extracted from the data lake, wherein the M sets of outbound calling fields include at least: fixed fields and user characteristic fields, and M is a positive integer; The format of the M groups of outbound call fields is converted to obtain the M groups of converted outbound call fields, and the M groups of converted outbound call fields are concatenated to obtain the processed outbound call fields; Obtain the object data of the target object, and fill the processed outbound call field and the object data into the initial outbound call strategy to obtain the outbound call strategy.

6. The method according to claim 1, characterized in that, Performing an outbound call operation on the target object according to the outbound call strategy includes: Obtain the outbound call preference type of the target object, wherein the outbound call preference type includes at least one of the following: device outbound call type and manual outbound call type; When the outbound call preference type of the target object is the device outbound call type, the outbound call strategy of the target object is uploaded to the outbound call system. When the outbound call system receives the outbound call strategy, it performs an outbound call operation on the target object according to the outbound call strategy. When the outbound call preference type is the manual outbound call type, the target client is obtained, and the outbound call strategy of the target object is sent to the target client. The target client refers to the client that is in an idle state selected from multiple candidate clients. The target client performs an outbound call operation on the target object according to the outbound call strategy.

7. The method according to claim 1, characterized in that, After performing an outbound call operation on the target object according to the outbound call strategy, the method further includes: Obtain the outbound call results of the target object, wherein the outbound call results refer to the results of the target object performing financial behavior based on the outbound call strategy; The financial label of the target object is adjusted based on the outbound call results to obtain the adjusted financial label, and the outbound call strategy of the target object is adjusted based on the adjusted financial label.

8. A strategy determination apparatus, characterized in that, include: The first acquisition unit is used to acquire the financial data of the target object when the target object authorizes it. The second acquisition unit is used to acquire a label recognition model, input financial data into the label recognition model, process it to obtain the financial label of the target object, wherein the label recognition model classifies the target object based on the target prompt words and the financial data to obtain the financial label, and the target prompt words include at least: defining the model role of the label recognition model, defining the content recognized by the label recognition model, and defining the output format of the label recognition model; The determining unit is configured to determine an outbound calling strategy based on the financial tag, and to perform an outbound calling operation on the target object according to the outbound calling strategy.

9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method for determining the strategy according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the method for determining the strategy according to any one of claims 1 to 7.

Images