Financial business query method and device, equipment, storage medium and product

Abstract

The invention discloses a financial business query method and device, equipment, a storage medium and a product. The method comprises the steps of obtaining financial service query data of a target user in response to a service query operation of the target user based on a query front-end interface; if the data type of the financial service query data is a text type, performing user intention prediction on the financial service query data according to a service query intention recognition model obtained by pre-training to obtain a user service query intention; determining target retrieval data according to the business query intention of the user; and according to the target retrieval data, generating a financial service query result, and displaying the financial service query result through a query front-end interface. According to the technical scheme of the invention, the efficient and accurate query of financial businesses is improved.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a financial business query method, device, equipment, storage medium and product. Background Art

[0002] In the field of financial technology, the processing of financial services is often accompanied by query requests for financial services, and different users often have different query requirements for financial services.

[0003] At present, financial business queries are usually based on rule-based query methods, or directly retrieve query results corresponding to matching requests from the corresponding database. However, due to the large number of query types in financial query services and different query methods for different users, it is often impossible to quickly and accurately feedback the query results expected by users. Therefore, quickly responding to user query requests and efficiently and accurately feedback the corresponding query results have become urgent problems to be solved in the current financial business query scenario. Summary of the invention

[0004] The present invention provides a financial business query method, device, equipment, storage medium and product to improve the efficient and accurate query of financial business.

[0005] According to one aspect of the present invention, a financial service query method is provided, the method comprising:

[0006] In response to a business query operation of a target user based on a query front-end interface, obtaining financial business query data of the target user;

[0007] If the data type of the financial business query data is a text type, user intent prediction is performed on the financial business query data according to a pre-trained business query intent recognition model to obtain the user business query intent;

[0008] Determining target retrieval data according to the user's business query intention;

[0009] The target data is retrieved to generate financial business query results, and the financial business query results are displayed through the query front-end interface.

[0010] According to another aspect of the present invention, a financial service query device is provided, the device comprising:

[0011] A data acquisition module, configured to acquire financial business query data of a target user in response to a business query operation of the target user based on the query front-end interface;

[0012] An intention prediction module, for predicting user intention on the financial business query data according to a pre-trained business query intention recognition model to obtain user business query intention if the data type of the financial business query data is a text type;

[0013] A data retrieval module, used to determine target retrieval data according to the user's business query intention;

[0014] The business query module is used to retrieve data according to the target, generate financial business query results, and display the financial business query results through the query front-end interface.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] 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 financial service query method described in any embodiment of the present invention.

[0019] 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 financial service query method described in any embodiment of the present invention when executed.

[0020] 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 financial service query method described above is implemented.

[0021] The technical solution of the embodiment of the present invention obtains the financial business query data of the target user, and when it is determined that the financial business query data is text data, the financial business query data is predicted by the business query intention recognition model obtained by pre-training to obtain the user's business query intention; the target retrieval data is determined according to the user's business query intention; and the financial business query result is generated according to the target retrieval data. The above technical solution combines the query scenarios in the financial business field, predicts the query intention of the target user, and retrieves relevant data based on the query intention, thereby determining the financial business query result, and performs business queries in a question-and-answer manner, thereby realizing human-computer interaction of financial business queries and bringing a good user experience; and improves the query efficiency and query accuracy of financial services.

[0022] 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

[0023] 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.

[0024] Figure 1 is a flow chart of a financial service query method provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is a flow chart of a financial service query method provided according to Embodiment 2 of the present invention;

[0026] Figure 3 is a schematic diagram of the structure of a financial service query device provided according to Embodiment 3 of the present invention;

[0027] Figure 4 It is a structural schematic diagram of an electronic device for implementing the financial service query method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] 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.

[0029] 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.

[0030] Embodiment 1

[0031] Figure 1 This is a flowchart of a financial service query method provided in the first embodiment of the present invention. This embodiment can be applied to the case of querying the same or different types of financial services initiated by relevant personnel. The method can be executed by a financial service query device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0032] S110 . In response to a business query operation of the target user based on a query front-end interface, obtain financial business query data of the target user.

[0033] S120: If the data type of the financial business query data is a text type, user intent is predicted for the financial business query data according to a pre-trained business query intent recognition model to obtain the user business query intent.

[0034] S130: Determine target retrieval data according to the user's business query intention.

[0035] S140. Generate financial business query results based on target retrieval data, and display the financial business query results through the query front-end interface.

[0036] The target user may be a user who has a financial service query requirement. The query front-end interface may be a front-end page for users to query financial services, and may specifically include a text input box, a voice input box, or a picture upload location for users to input.

[0037] Specifically, the target user can select a corresponding query method in the query front-end interface to perform a business query operation according to his actual needs. For example, the query method may include text input query, voice input query, or image upload query.

[0038] The target user's financial service query data is specifically query data input by the user based on the corresponding query method. For example, if a text input query method is used, the data type of the corresponding financial service query data is a text type; if a voice input query method is used, the data type of the corresponding financial service query data is a voice type, etc. For example, the financial service query data can be "Please help me check the remaining balance of the card number: XXX" or "How to perform a remittance operation", etc.

[0039] Among them, the business query intention recognition model is used to identify the query intention of the target user based on the financial business query data. For example, if the financial business query data input by the user is "how to transfer money", the business query intention recognition model may output the user's business query intention as "transfer operation or remittance operation", indicating that the user wants to know how to transfer or remit money, which belongs to the financial and payment operation requests.

[0040] This embodiment also provides a model training method for a business query intent recognition model, and the specific implementation process is as follows:

[0041] Collect query texts related to financial business queries in real scenarios as sample training sets, and annotate the intent category for each query text. For example, intent categories may include "balance query", "transfer remittance", "loan consultation" and "pay bills". Perform data preprocessing and data cleaning on the annotated query text sample data, such as removing stop words, vocabulary normalization, word segmentation and text deduplication and denoising. Convert the annotated query text sample data into a digital format that can be input into the machine learning model, such as text vectorization. Input the converted query text sample data into a pre-selected machine learning model for training until the model training end conditions are met, and obtain a business query intent recognition model that has completed the training. Among them, the machine learning model can be a support vector machine (Support Vector Machine, SVM) or RNN (Recurrent Neural Network, recursive neural network), etc.

[0042] Specifically, if the data type of the financial business query data is a text type, a pre-trained business query intention recognition model can be directly used to predict the user intention of the financial business query data and determine the user's business query intention.

[0043] Based on the user's business query intention, the financial business query data is retrieved to generate target retrieval data. For example, if the user's business query intention is "transfer operation", the data related to the transfer operation is retrieved from the corresponding database to obtain the target retrieval data. The target retrieval data can be directly fed back to the target user as the financial business query result through the query front-end interface. Alternatively, in order to further realize the interactivity between man and machine and improve the user's experience, the financial business query result can also be generated in a question-and-answer manner.

[0044] Specifically, the financial business query results are generated according to the target retrieval data, combined with the financial business query data and based on the natural language generation model. For example, if the financial business query data input by the target user is "how to perform a transfer operation", the target retrieval result obtained is "click the XX selection box on the application homepage to select remittance, enter the remittance page to fill in the remittance information, and confirm after completing the filling operation." Then the output result after processing based on the natural language generation model can be "For the transfer operation you expect to perform, you can first click the XX selection box of the application to select remittance, and fill in the remittance information after successfully entering the remittance page, check and inspect the filled content, and after the inspection is passed, you can complete the transfer operation by clicking the confirmation button. If you want to continue to understand other related issues with the transfer operation, please continue to enter financial business related questions."

[0045] The technical solution of the embodiment of the present invention obtains the financial business query data of the target user, and when it is determined that the financial business query data is text data, the financial business query data is predicted by the business query intention recognition model obtained by pre-training to obtain the user's business query intention; the target retrieval data is determined according to the user's business query intention; and the financial business query result is generated according to the target retrieval data. The above technical solution combines the query scenarios in the financial business field, predicts the query intention of the target user, and retrieves relevant data based on the query intention, thereby determining the financial business query result, and performs business queries in a question-and-answer manner, thereby realizing human-computer interaction of financial business queries and bringing a good user experience; and improves the query efficiency and query accuracy of financial services.

[0046] It is understandable that the data type of the financial service query data input by the target user based on the query front-end interface may also be voice-type data.

[0047] In an optional embodiment, after obtaining the target user's financial business query data, if the data type of the financial business query data is a voice type, the financial business query data is converted into text based on a pre-trained financial business voice recognition model to obtain the text-converted financial business query data; wherein the financial business voice recognition model is pre-trained based on audio data related to financial business.

[0048] This optional embodiment also provides a model training method for a financial business speech recognition model, which pre-trains the speech conversion model based on audio data related to financial business, thereby improving the recognition accuracy in the financial business speech recognition scenario.

[0049] Specifically, voice data related to financial services are collected as voice data training samples, and voice data in different formats are converted to standard formats. Each voice data training sample is annotated with speech-to-text conversion to obtain the real text label of each voice data training sample. The background noise of the voice data training sample is cleaned by noise elimination technology, and the audio signal is converted into features suitable for machine learning model processing. The voice data training samples annotated with real text labels are input into a preset voice recognition model for voice recognition to obtain predicted text; the voice recognition model is trained according to the predicted text and the real text to obtain a trained financial business voice recognition model.

[0050] The acquired voice-type financial business query data is input into a financial business speech recognition model for text conversion to obtain the financial business query data converted into text form.

[0051] The above technical solution improves the accuracy and reliability of text conversion of financial business query data by using a financial business speech recognition model pre-trained based on audio data related to financial business to convert financial business query data, thereby further improving the accuracy of recognition of subsequent user intentions.

[0052] It is understandable that the data type of the financial business query data input by the target user based on the query front-end interface may also be image-type data.

[0053] In an optional embodiment, after obtaining the target user's financial business query data, if the data type of the financial business query data is an image type, image recognition is performed on the financial business query data based on a pre-trained financial business image recognition model to generate image text description data; based on a pre-trained business query intention recognition model, user intent is predicted on the image text description data to obtain the user's business query intent.

[0054] The financial business recognition model is used to perform text prediction on image-type financial business query data. For example, if the financial business query data is an invoice, the image text description data predicted and recognized by the financial business recognition model may be "This image is an invoice image, where the invoice code is: XXX; the invoice date is: XXX; the invoice issuer is: XXX..."

[0055] This optional embodiment also provides a model training method for the financial business recognition model, which pre-trains the image-to-text conversion model based on image data related to financial business, thereby improving the recognition accuracy in the financial business image recognition scenario.

[0056] Specifically, collect image data related to financial business as image data training samples, and convert image data in different formats into standard formats. Annotate each image data training sample with image text description to obtain the real text description label of each image data training sample. Perform image enhancement on the image data training samples through image enhancement technology, and convert the image into features suitable for processing by the machine learning model. Input the image data training samples annotated with the real text description label into the preset image-text conversion model for text description recognition to obtain predicted text description data; according to the predicted text description data and the real text description label, perform model training on the image-text conversion model to obtain a trained financial business image recognition model.

[0057] The acquired image-type financial business query data is input into the financial business image recognition model for image recognition to obtain image text description data. According to the pre-trained business query intention recognition model, the user intention is predicted for the image text description data to obtain the user's business query intention.

[0058] The above technical solution performs image recognition on financial business query data by using a financial business image recognition model pre-trained based on image data related to financial business, thereby obtaining image text description data describing the financial business image, thereby improving the accuracy and reliability of determining the image text description data, thereby being able to further improve the accuracy of recognizing subsequent user intentions.

[0059] It should be noted that the search databases required for data search based on user business query intent may include external search databases and internal search databases. The internal search database is usually the business database of the bank's own internal business, and its security access rights are higher. The external search database is a public resource database that can be used by any resource demander for resource query or scheduling, and its security access rights are relatively low.

[0060] To ensure retrieval security, in an optional embodiment, target retrieval data is determined based on the user's business query intention, including: determining a target retrieval database based on the user's business query intention; if the target retrieval database is an external retrieval database, then based on the external retrieval database, performing information retrieval on the user's business query intention to obtain target retrieval data; or, if the target retrieval database is an internal retrieval database, then performing user identity authentication and user authority verification on the target user to obtain a verification result; if the verification result is that both user identity authentication and user authority verification are passed, then based on the internal retrieval database, performing information retrieval on the user's business query intention to obtain the target retrieval data.

[0061] For example, if the user's business query intent is "What information is needed to apply for a loan business", since this query intent does not involve the bank's internal data, the target search database can be an external search database. If the user's business query intent is "Help me check the balance of card number XXX", since this query intent is specific internal data of the bank's business, the target search database is an internal search database.

[0062] If the target search database is an external search database, a call request can be directly sent to the call interface of the external search database, and information retrieval is performed on the user's business query intention based on the external search database to obtain target search data.

[0063] If the target search database is an internal search database, due to the security of the internal search database, the target user's identity and permissions need to be verified to ensure the compliance, security and reliability of the query request. Specifically, the target user's user identity information can be obtained and verified, and the target user's user access rights can be verified to obtain the identity verification result and the permission verification result. If both the user identity verification and the user permission verification are passed, the user's business query intention is retrieved based on the internal search database to obtain the target search data.

[0064] The above technical solution determines the target retrieval database to be used according to the user's business query intention, and when it is determined that the target retrieval database to be used is an internal retrieval database, verifies the identity information and query authority of the target user, thereby ensuring the query reliability and security and avoiding the possibility of the target user's query information being maliciously obtained.

[0065] In an optional embodiment, after performing user identity authentication and user authority verification on the target user and obtaining the verification result, if the verification result is that the user identity authentication and / or user authority verification fails, target prompt information is generated and displayed on the query front-end interface, so that the target user can upload identity and authority proof data on the query front-end interface based on the target prompt information; if the identity and authority proof data uploaded by the target user is received within a preset time period, the identity and authority proof data is data verified to obtain a proof verification result; if the proof verification result passes, information retrieval is performed on the user's business query intention based on the internal retrieval database to obtain target retrieval data.

[0066] If any of the user identity verification results and user permission verification results fails, a target prompt message is generated. The target prompt message is used to prompt the verification result of the target user. For example, the target prompt message can be "Your identity verification or permission verification failed this time. Please upload other proof information to assist in verifying your identity or permission."

[0067] The target prompt information is displayed on the query front-end interface. After receiving the target prompt information, the user can choose to upload identity and authority proof data on the query front-end interface. The identity and authority proof data is used to assist in verifying the identity and / or rights of the target user. If the identity and authority proof data uploaded by the target user is received within the preset time period, the identity and authority proof data is subjected to data verification. Among them, the preset time period can be pre-set based on actual needs, in order to avoid the user's query request timeout. If the verification result of the identity and authority proof data passes, information retrieval is performed on the user's business query intention based on the internal retrieval database to obtain the target retrieval data.

[0068] The above-mentioned technical solution sends a target prompt message to the target user when it is determined that the user identity authentication and / or user authority verification has failed, thereby facilitating the target user to upload auxiliary proof information for identity and authority verification, thereby improving the flexibility and reliability of the target user's identity and authority verification, avoiding the possibility of misjudgment in the initial verification of the target user, and improving the target user's user experience of the query process.

[0069] In order to further improve the accuracy of identifying user intent and thus improve the accuracy of subsequent retrieval and query processes, the intent recognition model can also be optimized through the evaluation data of query results fed back by target users.

[0070] In an optional embodiment, after displaying the financial business query results through the query front-end interface, it also includes: obtaining the target user's result evaluation data on the financial business query results; and optimizing the business query intention recognition model based on the result evaluation data.

[0071] The target user can evaluate the accuracy of the financial business query results, specifically by evaluation score or grade (excellent, good, medium and poor, etc.). Based on the result evaluation data, it can be determined whether to use the current financial business query data and the user's business query intention as sample data for optimizing the business query intention recognition model. For example, if the evaluation grade of the result evaluation data meets the preset grade requirement, or the evaluation score is greater than the preset score threshold, the financial business query data and the user's business query intention of this query are used as optimized sample training data for optimizing the business query recognition model. The business query intention recognition model is optimized using the optimized sample training data within a period of time.

[0072] The above technical solution screens out optimized sample training data that can be used to optimize the business query intention recognition model under historical query cycles based on the target users' result evaluation data on the financial business query results, and uses the optimized sample training data to optimize the business query intention recognition model, thereby continuously improving the prediction accuracy of the business query intention recognition model.

[0073] 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.

[0074] Embodiment 2

[0075] Figure 2 This is a flow chart of a financial business query method provided in Embodiment 2 of the present invention. This embodiment provides a preferred example based on the above embodiments.

[0076] like Figure 2 As shown, the method comprises the following specific steps:

[0077] S210. In response to a business query operation of a target user based on a query front-end interface, obtain financial business query data of the target user.

[0078] S211A: If the data type of the financial business query data is a text type, execute S212.

[0079] S211B. If the data type of the financial business query data is a voice type, the financial business query data is converted into text based on a pre-trained financial business voice recognition model to obtain the text-converted financial business query data, and S212 is executed.

[0080] S211C. If the data type of the financial business query data is an image type, image recognition is performed on the financial business query data based on a pre-trained financial business image recognition model to generate image text description data, and the image text description data is used as the financial business query data to execute S212.

[0081] S212. Predict user intent on financial business query data based on the pre-trained business query intent recognition model to obtain user business query intent.

[0082] S213: Determine the target search database according to the user's business query intention. If the target search database is an external search database, execute S214; if the target search database is an internal search database, execute S215-S217.

[0083] S214: Based on the external search database, information search is performed on the user's business query intention to obtain target search data.

[0084] S215, perform user identity verification and user authority verification on the target user to obtain a verification result. If the verification result is that both the user identity verification and the user authority verification are passed, execute S216; if the verification result is that the user identity verification and / or the user authority verification are not passed, execute S217-S219;

[0085] S216: Based on the internal search database, information search is performed on the user's business query intention to obtain target search data.

[0086] S217, generating target prompt information, and displaying the target prompt information on the query front-end interface, so that the target user can upload identity authority certification data on the query front-end interface based on the target prompt information.

[0087] S218: If the identity and authority certification data uploaded by the target user is received within a preset time period, the identity and authority certification data is verified to obtain a certification verification result.

[0088] S219. If the verification result is passed, information retrieval is performed on the user's business query intention based on the internal retrieval database to obtain target retrieval data.

[0089] S220: Determine target retrieval data according to the user's business query intention.

[0090] S221. Generate financial business query results based on target retrieval data, and display the financial business query results through the query front-end interface.

[0091] Embodiment 3

[0092] Figure 3 The structure diagram of a financial service query device provided in the third embodiment of the present invention is shown in FIG. A financial service query device provided in the embodiment of the present invention can be applied to the case of querying the same or different types of financial services initiated by relevant personnel. The financial service query device can be implemented in the form of hardware and / or software, such as Figure 3 As shown, the device specifically includes: a data acquisition module 301, an intention prediction module 302, a data retrieval module 303 and a business query module 304. Among them,

[0093] The data acquisition module 301 is used to acquire the financial business query data of the target user in response to the business query operation of the target user based on the query front-end interface;

[0094] The intention prediction module 302 is used to predict the user intention of the financial business query data according to the pre-trained business query intention recognition model to obtain the user business query intention if the data type of the financial business query data is a text type;

[0095] The data retrieval module 303 is used to determine the target retrieval data according to the user's business query intention;

[0096] The business query module 304 is used to retrieve data according to the target, generate financial business query results, and display the financial business query results through the query front-end interface.

[0097] The technical solution of the embodiment of the present invention obtains the financial business query data of the target user, and when it is determined that the financial business query data is text data, the financial business query data is predicted by the business query intention recognition model obtained by pre-training to obtain the user's business query intention; the target retrieval data is determined according to the user's business query intention; and the financial business query result is generated according to the target retrieval data. The above technical solution combines the query scenarios in the financial business field, predicts the query intention of the target user, and retrieves relevant data based on the query intention, thereby determining the financial business query result, and performs business queries in a question-and-answer manner, thereby realizing human-computer interaction of financial business queries and bringing a good user experience; and improves the query efficiency and query accuracy of financial services.

[0098] Optionally, the device further comprises:

[0099] a voice data processing module, configured to, after acquiring the financial service query data of the target user, if the data type of the financial service query data is a voice type, perform text conversion on the financial service query data based on a pre-trained financial service speech recognition model to obtain text-converted financial service query data;

[0100] The financial business speech recognition model is pre-trained based on audio data related to financial business.

[0101] Optionally, the device further comprises:

[0102] an image data processing module, configured to, after acquiring the financial service query data of the target user, if the data type of the financial service query data is an image type, perform image recognition on the financial service query data based on a pre-trained financial service image recognition model to generate image text description data;

[0103] Accordingly, the intention prediction module 302 includes:

[0104] The intention prediction unit is used to predict the user intention of the image text description data according to the pre-trained business query intention recognition model to obtain the user business query intention.

[0105] Optionally, the data retrieval module 303 includes:

[0106] A database determination unit, used to determine a target retrieval database according to the user's business query intention;

[0107] An information retrieval unit, configured to perform information retrieval on the user's business query intention based on the external retrieval database to obtain target retrieval data if the target retrieval database is an external retrieval database; or

[0108] A verification unit, configured to perform user identity verification and user authority verification on the target user to obtain a verification result if the target search database is an internal search database;

[0109] The first information retrieval unit is used to perform information retrieval on the user's business query intention based on the internal retrieval database to obtain target retrieval data if the verification result is that both the user identity verification and the user authority verification are passed.

[0110] Optionally, the data retrieval module 303 further includes:

[0111] A prompt information generating unit is used for, after performing user identity verification and user authority verification on the target user and obtaining a verification result, if the verification result is that the user identity verification and / or user authority verification fails, generating target prompt information, and displaying the target prompt information on the query front-end interface, so that the target user can upload identity and authority certification data on the query front-end interface based on the target prompt information;

[0112] A data verification unit, configured to verify the identity and authority certification data uploaded by the target user within a preset time period, and obtain a certification verification result;

[0113] The second information retrieval unit is used to perform information retrieval on the user's business query intention based on the internal retrieval database to obtain target retrieval data if the proof verification result is passed.

[0114] Optionally, the device further comprises:

[0115] An evaluation data acquisition module, used for acquiring result evaluation data of the target user on the financial service query result after the financial service query result is displayed through the query front-end interface;

[0116] The model optimization module is used to optimize the business query intention recognition model according to the result evaluation data.

[0117] The financial service query device provided in the embodiment of the present invention can execute the financial service query method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0118] Embodiment 4

[0119] 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.

[0120] 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 the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0121] 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.

[0122] 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, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 executes the various methods and processes described above, such as a financial business query method.

[0123] In some embodiments, the financial business query method 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 financial business query method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to execute the financial business query method in any other appropriate manner (e.g., by means of firmware).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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 financial business query method, characterized in that: include: In response to a business query operation of a target user based on a query front-end interface, obtaining financial business query data of the target user; If the data type of the financial business query data is a text type, user intent prediction is performed on the financial business query data according to a pre-trained business query intent recognition model to obtain the user business query intent; Determining target retrieval data according to the user's business query intention; According to the target retrieval data, a financial business query result is generated, and the financial business query result is displayed through the query front-end interface.

2. The method according to claim 1, characterized in that After obtaining the financial service query data of the target user, the method further includes: If the data type of the financial service query data is a voice type, performing text conversion on the financial service query data based on a pre-trained financial service voice recognition model to obtain text-converted financial service query data; The financial business speech recognition model is pre-trained based on audio data related to financial business.

3. The method according to claim 1, characterized in that After obtaining the financial service query data of the target user, the method further includes: If the data type of the financial service query data is an image type, performing image recognition on the financial service query data based on a pre-trained financial service image recognition model to generate image text description data; Accordingly, the business query intention recognition model obtained by pre-training performs user intention prediction on the financial business query data to obtain the user business query intention, including: According to the pre-trained business query intention recognition model, the user intention is predicted on the image text description data to obtain the user business query intention.

4. The method according to claim 1, characterized in that: Determining target retrieval data according to the user's business query intention includes: Determining a target retrieval database according to the user's business query intention; If the target search database is an external search database, then based on the external search database, information search is performed on the user's business query intention to obtain target search data; or, If the target search database is an internal search database, user identity verification and user authority verification are performed on the target user to obtain a verification result; If the verification result is that both the user identity verification and the user authority verification are passed, then based on the internal search database, information retrieval is performed on the user's business query intention to obtain target retrieval data.

5. The method according to claim 4, characterized in that After performing user identity authentication and user authority authentication on the target user and obtaining the authentication result, the method further includes: If the verification result is that the user identity authentication and / or user authority verification fails, target prompt information is generated and displayed on the query front-end interface, so that the target user can upload identity and authority certification data on the query front-end interface based on the target prompt information; If the identity and authority certification data uploaded by the target user is received within a preset time period, the identity and authority certification data is verified to obtain a certification verification result; If the proof verification result is passed, information retrieval is performed on the user's business query intention based on the internal retrieval database to obtain target retrieval data.

6. The method according to claim 1, characterized in that After displaying the financial service query result through the query front-end interface, the method further includes: Obtaining result evaluation data of the target user on the financial service query result; According to the result evaluation data, the business query intention recognition model is optimized.

7. A financial business query device, characterized in that: include: A data acquisition module, configured to acquire financial business query data of a target user in response to a business query operation of the target user based on the query front-end interface; An intention prediction module, for predicting user intention on the financial business query data according to a pre-trained business query intention recognition model to obtain user business query intention if the data type of the financial business query data is a text type; A data retrieval module, used to determine target retrieval data according to the user's business query intention; The business query module is used to retrieve data according to the target, generate financial business query results, and display the financial business query results through the query front-end interface.

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 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 financial service query method 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 financial service query method 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, and when the computer program is executed by a processor, the computer program implements the financial service query method according to any one of claims 1 to 6.

Images