Strategy generation method and device based on financial business questions and answers, equipment, medium and product

Abstract

The invention discloses a strategy generation method and device based on financial business questions and answers, equipment, a medium and a product, and is applied to the technical field of finance. The method comprises the steps of determining a to-be-analyzed user communication record of a target user, performing feature analysis on the to-be-analyzed user communication record, and determining a target keyword and user demand information; determining a target intention prediction model according to the user demand information; determining user intention information based on a target intention prediction model according to the target keyword; and generating a user response strategy according to the user intention information, and sending the user response strategy to a financial business question and answer interface of the target user. According to the technical scheme, the user intention information can be determined through the to-be-analyzed user communication record, the user response strategy is generated, the efficiency and accuracy of financial feature analysis on the user are improved, and the effectiveness of a financial service strategy provided for the user and the satisfaction degree of the user are improved.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a strategy generation method, device, equipment, medium and product based on financial business question and answer. Background Art

[0002] With the continuous development of the Internet and digital technology, more and more banks in the financial industry have begun to use internal communication software to build social relationships with customers and provide customers with better financial services. At the same time, in the process of online communication, a lot of communication records with users will be generated, and the financial characteristics of users can be analyzed and marked by using past communication records, thereby providing users with more accurate and thoughtful financial services.

[0003] The existing communication record analysis method is usually based on manual analysis, but manual judgment is one-sided, subjective and forgetful. At the same time, there are many customers for employee marketing services. If the customer characteristics are forgotten or the marking is inaccurate, it will have a negative impact on subsequent marketing services, such as causing customer disgust. Secondly, when providing financial services based on customer marketing characteristics, it is also necessary to communicate with customers based on their own financial service knowledge and skills reserves. There are personal cognitive constraints on the breadth and depth of service coverage, which has certain limitations in recommending financial marketing strategies.

[0004] Therefore, how to utilize user communication records to improve the efficiency and accuracy of analyzing users' financial characteristics and financial business strategies, and to improve the effectiveness of the financial business strategies provided to users and user satisfaction, has become a technical problem that technical personnel urgently need to solve. Summary of the invention

[0005] The present invention provides a strategy generation method, device, equipment, medium and product based on financial business question and answer, so as to improve the efficiency and accuracy of financial feature analysis of users, and improve the effectiveness of financial business strategies provided to users and the user's satisfaction.

[0006] According to one aspect of the present invention, a strategy generation method based on financial business question and answer is provided, comprising:

[0007] Determine the user communication records to be analyzed of the target user, and perform feature analysis on the user communication records to be analyzed to determine target keywords and user demand information;

[0008] Determining a target intention prediction model according to the user demand information;

[0009] Determining user intent information according to the target keyword and based on the target intent prediction model;

[0010] A user response strategy is generated according to the user intention information, and the user response strategy is sent to the financial business question and answer interface of the target user.

[0011] According to another aspect of the present invention, there is provided a strategy generation device based on financial business question and answer, comprising:

[0012] A feature analysis module is used to determine the user communication records to be analyzed of the target user, and perform feature analysis on the user communication records to be analyzed to determine target keywords and user demand information;

[0013] An intention prediction model determination module is used to determine a target intention prediction model according to the user demand information;

[0014] An intention information determination module, used to determine user intention information according to the target keyword and based on the target intention prediction model;

[0015] A strategy generation module is used to generate a user response strategy based on the user intention information, and send the user response strategy to the financial business question and answer interface of the target user.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the strategy generation method based on financial business question and answer as described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the strategy generation method based on financial business question and answer as described in any embodiment of the present invention when executed.

[0021] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the strategy generation method based on financial business question and answer described in any embodiment of the present invention is implemented.

[0022] The technical solution of the embodiment of the present invention determines the user communication records to be analyzed of the target user, and performs feature analysis on the user communication records to be analyzed to determine the target keywords and user demand information; determines the target intention prediction model based on the user demand information; determines the user intention information based on the target keywords and the target intention prediction model; generates a user response strategy based on the user intention information, and sends the user response strategy to the financial business question and answer interface of the target user. This technical solution can determine the user intention of the target user through the communication records of the user to be analyzed, determine the user demand information and the corresponding target intention prediction model, and improve the efficiency and accuracy of analyzing the financial characteristics of the user; further, it can also generate a user response strategy based on the determined user intention information, thereby improving the effectiveness of the financial business strategy provided to the user and the user's satisfaction.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 is a flow chart of a strategy generation method based on financial business question and answer provided according to the first embodiment of the present invention;

[0026] Figure 2 is a flow chart of a strategy generation method based on financial business question and answer provided according to Embodiment 2 of the present invention;

[0027] Figure 3 1 is a schematic diagram of a structure of a strategy generation device based on financial business question and answer provided according to Embodiment 3 of the present invention;

[0028] Figure 4 It is a structural schematic diagram of an electronic device for implementing the strategy generation method based on financial business question and answer according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Embodiment 1

[0032] Figure 1 A flowchart of a strategy generation method based on financial business question and answer is provided for the first embodiment of the present invention. This embodiment is applicable to the case where the financial characteristics of the user are determined and financial business strategy recommendations are made based on the user communication records. The method can be executed by a strategy generation device based on financial business question and answer. The strategy generation device based on financial business question and answer can be implemented in the form of hardware and / or software. The strategy generation device based on financial business question and answer can be configured in an electronic device. Figure 1 As shown, the method includes:

[0033] S110 , determining the user communication records to be analyzed of the target user, and performing feature analysis on the user communication records to be analyzed to determine target keywords and user demand information.

[0034] The user communication records to be analyzed may be conversation records related to financial services generated when users use online chat applications, and may specifically be text records collected and authorized for communication through an enterprise's internal instant messaging application.

[0035] Among them, user demand information may be the financial business needs expressed by the user in the communication record, which may include business needs such as business process handling, financial product consultation and product details consultation.

[0036] Among them, the feature analysis of the communication records of the users to be analyzed may specifically be to extract and analyze the text content used to describe the user demand information in the communication records of the users to be analyzed, so as to determine the corresponding target keywords and the corresponding user demand information according to the communication records of the users to be analyzed. For example, the target keywords may include "XX service payment", "XX product details introduction" and "financial product recommendation", etc., and the corresponding user demand information may be "XX service processing flow", "XX product details consultation" and "financial product consultation recommendation", etc.

[0037] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with relevant laws, regulations and standards in relevant regions.

[0038] Optionally, feature analysis is performed on the user communication records to be analyzed to determine target keywords and user demand information, including: using a record feature analysis model obtained through pre-selection training to perform keyword extraction on the user communication records to be analyzed to obtain target keywords; wherein the record feature analysis model is obtained by pre-training a preset feature extraction model based on user communication record samples and pre-labeled sample keyword tags; and user demand information is determined based on the target keywords.

[0039] Specifically, the acquired user communication records to be analyzed can be used as the model input of the record feature analysis model, and the keywords in the communication records to be analyzed can be identified and extracted by the record feature analysis model, and the user communication records to be analyzed can be sliced ​​according to the extracted keywords, and the target keywords in different communication record segments can be obtained. Using the target keywords, the user's demand information can be determined. For example, if the target keywords include "XX product", "specific price information" and "product benefits", etc., the corresponding user demand information can be determined as "purchase details consultation for XX product", which is not specifically limited in this embodiment.

[0040] Furthermore, the training process of the record feature analysis model can be through a pre-built network model, using the acquired user communication record samples and the annotated sample keyword labels as the input of the network model, and obtaining the model prediction results of the model output for identifying and annotating the keywords in the user communication record samples. Furthermore, the model parameters of the network model can be adjusted according to the model prediction results and the actual results corresponding to the user communication record samples. Specifically, the model parameters of the network model can be adjusted through a gradient loss value algorithm or an optimization algorithm. And when the preset model training conditions are met, such as reaching a preset number of training times or meeting a set deviation threshold, the record feature analysis model can be obtained.

[0041] This technical solution can use the pre-built record feature analysis model to identify and extract target keywords in the communication records of the user to be analyzed, and determine the usage demand information. By using the record feature analysis model, the efficiency and accuracy of the financial feature analysis of the user are improved.

[0042] Optionally, determining the user communication records of the target user to be analyzed includes: obtaining the user communication records of the target user within a preset time period; performing feature analysis on the user communication records to determine the time characteristics and behavior characteristics of the user communication records; slicing the user communication records according to the time characteristics and behavior characteristics to determine at least one user communication sub-record; and determining each user communication sub-record as the user communication record to be analyzed.

[0043] The time feature may be used to indicate the time information of generating the user communication record, which may include year, month, day, X hour, X minute, X second, etc. The behavior feature may indicate all the user demand information during the communication process with the target user. The communication sub-record may be a user communication record segment used to record the various demand information of the target user.

[0044] Specifically, the user communication record to be analyzed may include all communication records of the user in a time period, such as all communication records with the target user within a week or a month, which may include all the user's demand information. Furthermore, the user communication record may be content sliced ​​according to the generation time of the user communication record and the user demand information in the user communication record, and the user communication sub-record containing the demand information of each user may be determined, and the sub-record may be determined as the user communication record to be analyzed. Exemplarily, the user communication record within a week may be obtained, where on Monday, the target user consulted about the handling process of XX business; on Thursday, the target user consulted about XX financial products. The user communication record may be content sliced ​​according to the time characteristics and behavior characteristics, and specifically, the handling process of XX business may be determined as the first communication sub-record, and the consultation on XX financial products may be determined as the second communication sub-record. Furthermore, the first sub-record and the second sub-record may be respectively determined as the user communication record to be analyzed.

[0045] This technical solution can slice the acquired user communication records according to time characteristics and behavior characteristics, so as to obtain the user communication to be analyzed under different user needs. The efficiency and accuracy of financial feature analysis of users can be improved by finely segmenting user communication records and performing differentiated processing on user communication records containing different behavior characteristics.

[0046] S120: Determine a target intention prediction model based on user demand information.

[0047] Specifically, after determining the user demand information of the target user, a prediction model for determining the user's target intention can be obtained. The target intention prediction model can correspond to the user demand information, and can specifically include various types of intention prediction models such as business process handling, financial product consultation, and product details consultation.

[0048] S130: Determine user intent information according to the target keyword and based on the target intent prediction model.

[0049] Specifically, the target keywords in the communication records to be analyzed of the target user can be obtained as the model input of the target intention prediction model, and then the user intention information of the target user can be obtained through the target intention prediction model. For example, the target keywords are "XX business", "execution process" or "business processing result evaluation", etc. The target intention prediction model can be determined as a business process processing prediction model based on user demand information, and the user intention information can be determined as the intention result of business processing and evaluation.

[0050] S140. Generate a user response strategy based on the user intention information, and send the user response strategy to the financial business question and answer interface of the target user.

[0051] Among them, the user response strategy can be a business processing strategy generated according to the user's intention. Specifically, the corresponding business processing flow information can be directly generated according to the user's intention information, and the generated business processing flow information can be fed back to the target user's financial business question and answer interface. Exemplarily, continuing the above example, if the user's intention information is the processing flow of XX business, the specific processing flow of XX business can be generated and fed back to the target user.

[0052] Optionally, after sending the user response strategy to the target user's financial business question-and-answer interface, it also includes: obtaining the target user's strategy evaluation result on the user response strategy based on the financial business question-and-answer interface; and updating the target intention prediction model according to the strategy evaluation result.

[0053] The strategy evaluation result may be a feedback result of the target user's satisfaction with the generated user response strategy, and specific evaluation results may include very satisfied, satisfied, average, dissatisfied, etc.

[0054] Specifically, the target user can process the corresponding financial business according to the received user response strategy and evaluate the user response strategy. Furthermore, the target intention prediction model can be updated according to the obtained strategy evaluation result. Exemplarily, the strategy evaluation result threshold can be set in advance. If the evaluation result is very satisfactory or satisfactory, the model prediction result of the current target intention prediction model can be continued, and the corresponding user response strategy can be directly generated according to the model prediction result; if the evaluation result is general or unsatisfactory, it can be determined that the target intention prediction model needs to be updated until the strategy evaluation result of the user response strategy generated according to the model prediction result is very satisfactory or satisfactory, then the update of the target intention prediction model is stopped. This embodiment does not impose specific restrictions on this.

[0055] This technical solution can update the target intention prediction model according to the evaluation results of the target user on the user response strategy, further improving the effectiveness of the financial business strategy provided to the user and the user's satisfaction.

[0056] The technical solution of the embodiment of the present invention determines the user communication records to be analyzed of the target user, and performs feature analysis on the user communication records to be analyzed to determine the target keywords and user demand information; determines the target intention prediction model based on the user demand information; determines the user intention information based on the target keywords and the target intention prediction model; generates a user response strategy based on the user intention information, and sends the user response strategy to the financial business question and answer interface of the target user. This technical solution can determine the user intention of the target user through the user communication records to be analyzed, determine the user demand information and the corresponding target intention prediction model, and improve the efficiency and accuracy of the financial feature analysis of the user; further, it can also generate a user response strategy based on the determined user intention information, thereby improving the effectiveness of the financial business strategy provided to the user and the user's satisfaction.

[0057] Embodiment 2

[0058] Figure 2 This is a flow chart of a strategy generation method based on financial business question and answer provided in the second embodiment of the present invention. Based on the above embodiment, this embodiment further optimizes the above strategy generation method based on financial business question and answer.

[0059] Further, the step "determine user intent information based on the target keyword and the target intention prediction model" is refined into "if the target intention prediction model is a product detail intention prediction model, then the target keyword is input into the product detail consultation intention prediction model to obtain the product intention result output by the model; if the target intention prediction model is a business handling intention prediction model, then the target keyword is input into the business handling intention prediction model to obtain the satisfaction level of the handling result output by the model; if the target intention prediction model is a product consultation intention prediction model, then the target keyword is input into the product consultation intention prediction model to obtain the predicted recommended product output by the model; the product intention result or the satisfaction level of the handling result or the predicted recommended product is used as the user intent information." to improve the method of generating the user access permission list. Figure 2 As shown, the method includes:

[0060] S210: Determine the user communication records to be analyzed of the target user, perform feature analysis on the user communication records to be analyzed, and determine target keywords and user demand information.

[0061] S220: Determine a target intention prediction model based on user demand information.

[0062] S230: If the target intention prediction model is a product details intention prediction model, the target keyword is input into the product details consultation intention prediction model to obtain the product intention result output by the model.

[0063] Specifically, when the user demand information is for consulting on the details of a financial product, the product details intention prediction model can be determined as the target intention prediction model, and the target keywords related to consulting on the details of the financial product can be input into the product details intention prediction model, and the user's product intention results can be output through the model. The product intention results can be the user's desire to buy the financial product and the interest level. Exemplarily, when the communication record of the user to be analyzed contains a demand for detailed consultation on XX financial products, the target intention prediction model can be determined to be the product details intention prediction model. Then, the target keywords, such as product name, product logo, product price and revenue, can be input into the product details intention prediction model, and the product intention results of the target user for XX financial products can be obtained, such as a high desire to buy, a high interest level, etc.

[0064] S240. If the target intention prediction model is a business processing intention prediction model, the target keyword is input into the business processing intention prediction model to obtain the satisfaction level of the processing result output by the model.

[0065] Specifically, when the user demand information is business process consultation, the business processing intention prediction model can be determined as the target intention prediction model, and the target keywords related to the business processing process consultation are input into the business processing intention prediction model, and the model can be used to output the user's satisfaction with the business processing results. The result satisfaction can be very satisfied, satisfied, general, and dissatisfied, etc. Exemplarily, when the user communication record to be analyzed contains the demand for XX business processing process consultation, the target intention prediction model can be determined as the business processing intention prediction model. Then, the target keywords, such as business name, business logo, and business processing result information, can be input into the product details intention prediction model, and the target user's satisfaction with the XX business processing result can be obtained, such as being very satisfied with the business processing result, or being dissatisfied with the business processing result, etc.

[0066] S250: If the target intention prediction model is a product consultation intention prediction model, the target keyword is input into the product consultation intention prediction model to obtain the predicted recommended product output by the model.

[0067] Specifically, when the user demand information is for financial product consultation, the product consultation intention prediction model can be determined as the target intention prediction model. Furthermore, when the target user does not clearly indicate a specific financial product and provides financial product consultation, the product consultation intention prediction model can be determined as the target intention prediction model, and the target keywords related to financial product consultation are input into the product consultation intention prediction model to predict and recommend financial products to the target user. Among them, the prediction and recommendation of financial products can be based on target keywords, such as the product type and detailed information of the financial product, and combined with the user information provided by the target user to predict and recommend financial products.

[0068] S260: Use the product intention result or the satisfaction degree of the processing result or the predicted recommended product as the user intention information.

[0069] Specifically, when the user demand information is for consultation on the details of a financial product, the product details intention prediction model can be used to output the product intention result and use it as the user intention information of the target user; when the user demand information is for consultation on the business processing flow, the business processing intention prediction model can be used to output the satisfaction level of the business processing result and use it as the user intention information of the target user; and when the user demand information is for consultation on financial products, the product consultation intention prediction model can be used to output predicted recommended products and use them as the user intention information of the target user.

[0070] S270. Generate a user response strategy based on the user intention information, and send the user response strategy to the financial business question and answer interface of the target user.

[0071] Optionally, a user response strategy is generated based on the user intention information, including: if the user intention information is a product intention result, then a product response strategy is generated based on the product intention result; if the user intention information is the satisfaction level with the processing result, then a business response strategy is generated based on the satisfaction level with the processing result; if the user intention information is a predicted recommended product, then a target recommendation strategy is generated based on the predicted recommended product; and the product response strategy, the business response strategy or the target recommendation strategy is used as the user response strategy.

[0072] Specifically, when the user intention information is a product intention result, a corresponding product response strategy can be generated according to the target user's desire to purchase the financial product and the interest level. For example, if the target user has a high desire to purchase the financial product or has a high interest level, a purchase coupon for the financial product can be generated and distributed to the target user; if the target user has a low desire to purchase the financial product or has a low interest level, a purchase coupon for the financial product can also be generated, and the target user can also be recommended financial products of the same type for selection.

[0073] Specifically, when the user intent information is the satisfaction level of the processing result, a corresponding business response strategy can be generated according to the target user's satisfaction level with the business processing. Exemplarily, if the target user is dissatisfied with the result of the business processing, a general voucher can be generated and distributed to the user as a consolation; at the same time, the processing flow of the business can be optimized to avoid similar situations from happening again. Furthermore, when the user intent information is a predicted recommended product, a target recommendation strategy is generated based on the predicted recommended product, wherein the target recommendation strategy can specifically generate product details information and corresponding product purchase links of the predicted recommended product, as well as purchase coupons for the predicted recommended product, when the predicted recommended product is obtained, and send them to the user as a user response strategy for the target user.

[0074] This technical solution can generate corresponding response strategies according to different user target intention information, and use the generated response strategies as user response strategies, thereby improving the effectiveness of the financial business strategies generated for users and user satisfaction.

[0075] The technical solution of the embodiment of the present invention determines the user communication records to be analyzed of the target user, and performs feature analysis on the user communication records to be analyzed to determine the target keywords and user demand information; according to the user demand information, the target intention prediction model is determined; if the target intention prediction model is a product detail intention prediction model, the product intention result output by the model is obtained; if the target intention prediction model is a business handling intention prediction model, the satisfaction degree of the handling result output by the model is obtained; if the target intention prediction model is a product consultation intention prediction model, the predicted recommended product output by the model is obtained; the product intention result or the satisfaction degree of the handling result or the predicted recommended product is used as the user intention information; according to the user intention information, a user response strategy is generated, and the user response strategy is sent to the financial business question and answer interface of the target user. This technical solution can determine different target intention prediction models according to the user's demand information, and obtain the corresponding user intention information, thereby generating a user response strategy, improving the efficiency and accuracy of the financial feature analysis of the user, and improving the effectiveness of the financial business strategy provided to the user and the user's satisfaction.

[0076] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data comply with relevant laws, regulations and standards in relevant regions.

[0077] Embodiment 3

[0078] Figure 3The schematic diagram of the structure of a strategy generation device based on financial business question and answer provided in the third embodiment of the present invention. The strategy generation device based on financial business question and answer provided in the embodiment of the present invention can be applied to the situation where the financial characteristics of the user are determined based on the user communication record and financial business strategy is recommended. The strategy generation device based on financial business question and answer can be implemented in the form of hardware and / or software, such as Figure 3 As shown, it specifically includes: a feature analysis module 310, an intention prediction model determination module 320, an intention information determination module 330 and a strategy generation module 340.

[0079] in,

[0080] The feature analysis module 310 is used to determine the user communication records to be analyzed of the target user, and perform feature analysis on the user communication records to be analyzed to determine target keywords and user demand information;

[0081] An intention prediction model determination module 320 is used to determine a target intention prediction model according to the user demand information;

[0082] An intention information determination module 330, configured to determine user intention information according to the target keyword and based on the target intention prediction model;

[0083] The strategy generation module 340 is used to generate a user response strategy according to the user intention information, and send the user response strategy to the financial business question and answer interface of the target user.

[0084] This technical solution can determine the user demand information and the corresponding target intention prediction model through the communication records of the users to be analyzed, and determine the user intentions of the target users, thereby improving the efficiency and accuracy of financial feature analysis of users; furthermore, it can also generate user response strategies based on the determined user intention information, thereby improving the effectiveness of the financial business strategies provided to users and user satisfaction.

[0085] Optionally, the feature analysis module 310 is specifically used to use the record feature analysis model obtained through pre-selected training to extract keywords from the user communication record to be analyzed to obtain target keywords; wherein the record feature analysis model is obtained by pre-training a preset feature extraction model based on user communication record samples and pre-labeled sample keyword tags;

[0086] According to the target keywords, user demand information is determined.

[0087] Optionally, the intention prediction model determination module 320 is specifically configured to input the target keyword into the product details intention prediction model to obtain a product intention result output by the model if the target intention prediction model is a product details intention prediction model;

[0088] If the target intention prediction model is a business handling intention prediction model, the target keyword is input into the business handling intention prediction model to obtain the satisfaction degree of the handling result output by the model;

[0089] If the target intention prediction model is a product consultation intention prediction model, the target keyword is input into the product consultation intention prediction model to obtain a predicted recommended product output by the model;

[0090] The product intention result or the satisfaction degree of the processing result or the predicted recommended product is used as the user intention information.

[0091] Optionally, the strategy generation module 340 is specifically configured to:

[0092] If the user intention information is a product intention result, generating a product response strategy according to the product intention result;

[0093] If the user intention information is the degree of satisfaction with the processing result, then generating a business response strategy according to the degree of satisfaction with the processing result;

[0094] If the user intention information is a predicted recommended product, generating a target recommendation strategy based on the predicted recommended product;

[0095] The product response strategy or business response strategy or target recommendation strategy is used as the user response strategy.

[0096] Optionally, the feature analysis module 310 is further configured to obtain user communication records of the target user within a preset time period;

[0097] Performing feature analysis on the user communication records to determine time features and behavior features of the user communication records;

[0098] Slice the user communication record according to the time feature and the behavior feature to determine at least one user communication sub-record;

[0099] Each of the user communication sub-records is determined as a user communication record to be analyzed.

[0100] Optionally, the device further comprises: a strategy adjustment module, configured to, after sending the user response strategy to the financial service question-and-answer interface of the target user,

[0101] Obtaining a strategy evaluation result of the target user on the user response strategy based on the financial business question-and-answer interface;

[0102] According to the strategy evaluation result, the target intention prediction model is updated.

[0103] The strategy generation device based on financial business question and answer provided in the embodiment of the present invention can execute the strategy generation method based on financial business question and answer provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0104] Embodiment 4

[0105] Figure 4 A schematic diagram of the structure of an electronic device 40 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0106] like Figure 4 As shown, the electronic device 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In RAM43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, ROM42 and RAM43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0107] A number of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0108] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 41 executes the various methods and processes described above, such as a strategy generation method based on financial business question and answer.

[0109] In some embodiments, the strategy generation method based on financial business questions and answers may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the strategy generation method based on financial business questions and answers described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the strategy generation method based on financial business questions and answers in any other appropriate manner (e.g., by means of firmware).

[0110] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0112] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0114] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0115] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0116] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0117] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A strategy generation method based on financial business question and answer, characterized in that: include: Determine the user communication records to be analyzed of the target user, and perform feature analysis on the user communication records to be analyzed to determine target keywords and user demand information; Determining a target intention prediction model according to the user demand information; Determining user intent information according to the target keyword and based on the target intent prediction model; A user response strategy is generated according to the user intention information, and the user response strategy is sent to the financial business question and answer interface of the target user.

2. The method according to claim 1, characterized in that The feature analysis of the communication records of the user to be analyzed to determine target keywords and user demand information includes: Using the record feature analysis model obtained through pre-selection training, keywords are extracted from the communication record of the user to be analyzed to obtain target keywords; wherein the record feature analysis model is obtained by pre-training a preset feature extraction model based on user communication record samples and pre-labeled sample keyword labels; According to the target keywords, user demand information is determined.

3. The method according to claim 1, characterized in that: Determining user intention information according to the target keyword and based on the target intention prediction model includes: If the target intention prediction model is a product details intention prediction model, the target keyword is input into the product details intention prediction model to obtain a product intention result output by the model; If the target intention prediction model is a business handling intention prediction model, the target keyword is input into the business handling intention prediction model to obtain the satisfaction degree of the handling result output by the model; If the target intention prediction model is a product consultation intention prediction model, the target keyword is input into the product consultation intention prediction model to obtain a predicted recommended product output by the model; The product intention result or the satisfaction degree of the processing result or the predicted recommended product is used as the user intention information.

4. The method according to claim 3, characterized in that Generating a user response strategy according to the user intention information includes: If the user intention information is a product intention result, generating a product response strategy according to the product intention result; If the user intention information is the degree of satisfaction with the processing result, then generating a business response strategy according to the degree of satisfaction with the processing result; If the user intention information is a predicted recommended product, generating a target recommendation strategy based on the predicted recommended product; The product response strategy or business response strategy or target recommendation strategy is used as the user response strategy.

5. The method according to claim 1, characterized in that The communication records of the target user to be analyzed include: Obtain user communication records of target users within a preset time period; Performing feature analysis on the user communication records to determine time features and behavior features of the user communication records; Slice the user communication record according to the time feature and the behavior feature to determine at least one user communication sub-record; Each of the user communication sub-records is determined as a user communication record to be analyzed.

6. The method according to claim 1, characterized in that After sending the user response strategy to the financial business question-and-answer interface of the target user, the method further includes: Obtaining a strategy evaluation result of the target user on the user response strategy based on the financial business question-and-answer interface; According to the strategy evaluation result, the target intention prediction model is updated.

7. A strategy generation device based on financial business question and answer, characterized in that: include: A feature analysis module is used to determine the user communication records to be analyzed of the target user, and perform feature analysis on the user communication records to be analyzed to determine target keywords and user demand information; An intention prediction model determination module is used to determine a target intention prediction model according to the user demand information; An intention information determination module, used to determine user intention information according to the target keyword and based on the target intention prediction model; A strategy generation module is used to generate a user response strategy based on the user intention information, and send the user response strategy to the financial business question and answer interface of the target user.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the strategy generation method based on financial business question and answer according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the strategy generation method based on financial business question and answer according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the strategy generation method based on financial business question and answer according to any one of claims 1 to 6.

Images