CN117333291A

CN117333291A - Financial product data processing method and device, storage medium and electronic equipment

Info

Publication number: CN117333291A
Application number: CN202311016381.8A
Authority: CN
Inventors: 兰亭
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-08-11
Filing date: 2023-08-11
Publication date: 2024-01-02

Abstract

The application discloses a processing method and device of financial product data, a storage medium and electronic equipment, and relates to the field of financial science and technology, wherein the method comprises the following steps: acquiring keyword information in product information of a target financial product; translating the keyword information according to a preset word list to obtain a first translation result of a target language corresponding to the keyword information; pushing the first translation result and the keyword information to a target object, and judging whether a selection instruction of the target object on the first translation result is received or not; if a selection instruction is received, acquiring product information of a target financial product and acquiring a target translation result of a target language corresponding to the product information; and pushing the product information and the target translation result to the target object. According to the method and the device, the problem that the data processing efficiency is low due to the fact that a large amount of system resources are occupied because bilingual translation and display are directly carried out on the complete introduction information of the financial product in the related technology is solved.

Description

Financial product data processing method and device, storage medium and electronic equipment

Technical Field

The present application relates to the field of financial science and technology, and in particular, to a method and apparatus for processing financial product data, a storage medium, and an electronic device.

Background

In the global context, the financial industry needs to provide customers with bilingual services on product descriptions of financial products, which often require a significant amount of time for a translator to translate the product descriptions of financial products in order to ensure accuracy of the bilingual services. For newly released financial products, when corresponding bilingual services are provided for customers, if complete specifications of the financial products are translated, a large amount of system resources are occupied, so that the processing efficiency of product data of the financial products is low, and further, the customers cannot acquire bilingual introduction of the newly-online financial products at the first time.

Aiming at the problem that the data processing efficiency is low because a large amount of system resources are occupied by directly performing bilingual translation and display on complete introduction information of financial products in the related technology, no effective solution is proposed at present.

Disclosure of Invention

The main purpose of the application is to provide a processing method and device for financial product data, a storage medium and electronic equipment, so as to solve the problem that the related technology directly translates and displays the complete introduction information of the financial product in bilingual manner, so that a large amount of system resources are occupied, and the data processing efficiency is low.

In order to achieve the above object, according to one aspect of the present application, there is provided a processing method of financial product data. The method comprises the following steps: obtaining keyword information in product information of a target financial product, wherein the keyword information comprises at least one of the following components: product name, product type, product period and risk information of the target financial product; translating the keyword information according to a preset word list to obtain a first translation result of a target language corresponding to the keyword information; pushing the first translation result and the keyword information to a target object, and judging whether a selection instruction of the target object on the first translation result is received or not; if the selection instruction is received, acquiring product information of the target financial product and acquiring a target translation result of a target language corresponding to the product information; pushing the product information and the target translation result to the target object.

Further, translating the keyword information according to a preset word list, and obtaining a first translation result of the target language corresponding to the keyword information includes: translating the keyword information according to a preset word list to obtain an initial translation result; and acquiring a first correction result of the initial translation result, and updating the initial translation result according to the first correction result to obtain the first translation result.

Further, obtaining the target translation result of the target language corresponding to the product information includes: carrying out sentence splitting on the product information of the target financial product to obtain a plurality of split sentences; processing the multiple split sentences through a first machine translation model to obtain second translation results of target languages corresponding to the multiple split sentences; combining the second translation results of the target languages corresponding to the divided sentences to obtain a third translation result; and obtaining a second correction result of the third translation result, and updating the third translation result according to the second correction result to obtain the target translation result.

Further, obtaining a second correction result to the third translation result includes: acquiring first historical click volume data of the target financial product and second historical click volume data of financial products of non-target financial products; determining a verification order of product information of the target financial product according to the first historical click quantity data and the second historical click quantity data; and according to the proofreading order, proofreading the third translation result to obtain a second proofreading result of the third translation result.

Further, after updating the third translation result according to the second calibration result to obtain the target translation result, the method further includes: determining a positive sample set according to the product information of the target financial product and the target translation result; determining a negative sample set according to the product information of the target financial product and the third translation result; training the first machine translation model through the positive sample set and the negative sample set to obtain a second machine translation model; judging whether to update the first machine translation model according to the second machine translation model to obtain a target judgment result; and if the target judgment result characterization updates the first machine translation model, updating the second machine translation model into the first machine translation model.

Further, according to the second machine translation model, determining whether to update the first machine translation model, and obtaining a target determination result includes: obtaining a test sample set, wherein the test sample set at least comprises product information of a plurality of financial products and real translation results of target languages corresponding to the financial product information; translating the product information of the financial products in the test sample set through the first machine translation model to obtain a fourth translation result; translating the product information of the financial products in the test sample set through the second machine translation model to obtain a fifth translation result; calculating a first translation accuracy corresponding to the fourth translation result according to the real translation result; calculating a second translation accuracy corresponding to the fifth translation result according to the real translation result; and judging whether to update the first machine translation model according to the first translation accuracy and the second translation accuracy to obtain the target judgment result.

Further, according to the first translation accuracy and the second translation accuracy, determining whether to update the first machine translation model, and obtaining the target determination result includes: judging whether the second translation accuracy rate is greater than the first translation accuracy rate; if the second translation accuracy is greater than the first translation accuracy, determining that the target judgment result is that the first machine translation model is updated; and if the second translation accuracy is smaller than or equal to the first translation accuracy, determining that the target judgment result is that the first machine translation model is not updated.

In order to achieve the above object, according to another aspect of the present application, there is provided a processing apparatus of financial product data. The device comprises: a first obtaining unit, configured to obtain keyword information in product information of a target financial product, where the keyword information includes at least one of the following: product name, product type, product period and risk information of the target financial product; the translation unit is used for translating the keyword information according to a preset word list to obtain a first translation result of a target language corresponding to the keyword information; the first pushing unit is used for pushing the first translation result and the keyword information to a target object and judging whether a selection instruction of the target object on the first translation result is received or not; the second obtaining unit is used for obtaining the product information of the target financial product and obtaining a target translation result of a target language corresponding to the product information if the selection instruction is received; and the second pushing unit is used for pushing the product information and the target translation result to the target object.

Further, the translation unit includes: the first translation module is used for translating the keyword information according to a preset word list to obtain an initial translation result; the first acquisition module is used for acquiring a first correction result of the initial translation result, updating the initial translation result according to the first correction result, and obtaining the first translation result.

Further, the second acquisition unit includes: the splitting module is used for splitting the sentences of the product information of the target financial product to obtain a plurality of split sentences; the processing module is used for processing the plurality of split sentences through the first machine translation model to obtain second translation results of target languages corresponding to the plurality of split sentences; the merging module is used for merging the second translation results of the target languages corresponding to the split sentences to obtain a third translation result; the second obtaining module is used for obtaining a second proofreading result of the third translation result, and updating the third translation result according to the second proofreading result to obtain the target translation result.

Further, the second acquisition module includes: an acquisition sub-module for acquiring first historical click volume data of the target financial product and second historical click volume data of financial products other than the target financial product; a determining submodule, configured to determine a collation order of product information of the target financial product according to the first historical click volume data and the second historical click volume data; and the checking sub-module is used for checking the third translation result according to the checking sequence to obtain a second checking result of the third translation result.

Further, after updating the third translation result according to the second collation result to obtain the target translation result, the apparatus further includes: a first determining unit, configured to determine a positive sample set according to product information of the target financial product and the target translation result; a second determining unit, configured to determine a negative sample set according to the product information of the target financial product and the third translation result; the training unit is used for training the first machine translation model through the positive sample set and the negative sample set to obtain a second machine translation model; the judging unit is used for judging whether the first machine translation model is updated according to the second machine translation model to obtain a target judging result; and the updating unit is used for updating the second machine translation model into the first machine translation model if the target judgment result represents that the first machine translation model is updated.

Further, the judging unit includes: the third acquisition module is used for acquiring a test sample set, wherein the test sample set at least comprises product information of a plurality of financial products and real translation results of target languages corresponding to the information of each financial product; the second translation module is used for translating the product information of the financial products in the test sample set through the first machine translation model to obtain a fourth translation result; the third translation module is used for translating the product information of the financial products in the test sample set through the second machine translation model to obtain a fifth translation result; the first calculation module is used for calculating a first translation accuracy rate corresponding to the fourth translation result according to the real translation result; the second calculation module is used for calculating a second translation accuracy rate corresponding to the fifth translation result according to the real translation result; and the judging module is used for judging whether the first machine translation model is updated according to the first translation accuracy and the second translation accuracy to obtain the target judging result.

Further, the judging module includes: the judging submodule is used for judging whether the second translation accuracy rate is larger than the first translation accuracy rate or not; the first determining submodule is used for determining that the target judgment result is to update the first machine translation model if the second translation accuracy is greater than the first translation accuracy; and the second determination submodule is used for determining that the target judgment result is that the first machine translation model is not updated if the second translation accuracy is smaller than or equal to the first translation accuracy.

In order to achieve the above object, according to an aspect of the present application, there is provided a computer-readable storage medium storing a program, wherein the program, when run, controls a device in which the storage medium is located to execute the processing method of financial product data of any one of the above.

To achieve the above object, according to another aspect of the present application, there is also provided an electronic device including one or more processors and a memory for storing a processing method for the one or more processors to implement the financial product data described in any one of the above.

Through the application, the following steps are adopted: obtaining keyword information in product information of a target financial product, wherein the keyword information comprises at least one of the following components: product name, product type, product deadline, and risk information for the target financial product; translating the keyword information according to a preset word list to obtain a first translation result of a target language corresponding to the keyword information; pushing the first translation result and the keyword information to a target object, and judging whether a selection instruction of the target object on the first translation result is received or not; if a selection instruction is received, acquiring product information of a target financial product and acquiring a target translation result of a target language corresponding to the product information; the product information and the target translation result are pushed to the target object, so that the problem that the data processing efficiency is low due to the fact that a large amount of system resources are occupied because the whole introduction information of the financial product is directly translated and displayed in bilingual mode in the related technology is solved. In the application, the keyword information of the target financial product is translated firstly, the translation result of the keyword information is pushed to the target object, then whether the complete product information of the target financial product is translated or not is determined according to the selection information of the target object on the keyword result, the direct full-text translation of the product information of the financial product is avoided, and the effect of improving the processing efficiency of the data information of the financial product is achieved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:

FIG. 1 is a flow chart of a method of processing financial product data provided in accordance with an embodiment of the present application;

FIG. 2 is a flowchart of a method for processing financial product data according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a processing device for financial product data provided in accordance with an embodiment of the present application;

fig. 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application.

Detailed Description

It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that, related information (including, but not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by a user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.

The present invention will be described with reference to preferred implementation steps, and fig. 1 is a flowchart of a method for processing financial product data according to an embodiment of the present application, as shown in fig. 1, and the method includes the following steps:

step S101, obtaining keyword information in product information of a target financial product, wherein the keyword information comprises at least one of the following components: product name, product type, product deadline, and risk information for the target financial product.

For example, keyword information having a relatively large influence on the selection of a customer, such as information of the name of the product, the type of the product, the term of the product, the risk level of the product, and the like, in the product specification (i.e., the product information described above) of a target financial product (e.g., financial product) is acquired.

Step S102, translating the keyword information according to a preset word list to obtain a first translation result of the target language corresponding to the keyword information.

For example, the obtained keyword information is translated according to a preset common vocabulary (i.e., the preset vocabulary) to obtain a keyword translation result (i.e., the first translation result) of the target language (e.g., english) of the keyword information.

Step S103, pushing the first translation result and the keyword information to the target object, and judging whether a selection instruction of the target object for the first translation result is received or not.

For example, the keyword translation result and the keyword text are pushed to the customer (i.e. the target object) through the service page of the financial product, and then it is determined whether a translation instruction (i.e. the selection instruction) for selecting the full text translation of the product specification of the target financial product according to the keyword translation result by the customer is received.

Step S104, if a selection instruction is received, obtaining product information of a target financial product and obtaining a target translation result of a target language corresponding to the product information.

For example, if a translation instruction selected by the customer is received, a complete product specification of the target financial product and a full text translation result (i.e., the target translation result) of the product specification corresponding to the target language are obtained.

Step S105, pushing the product information and the target translation result to the target object.

For example, after the product specification and the full text translation result of the target financial product are obtained, the product specification and the full text translation result are pushed to the customer through the service page of the financial product.

In summary, in the application, the keyword information of the target financial product is translated first, the translation result of the keyword information is pushed to the target object, and then whether the complete product information of the target financial product is translated or not is determined according to the selection information of the keyword result of the target object, so that the full-text translation of the product information of the financial product is avoided, and the effect of improving the processing efficiency of the data information of the financial product is achieved.

Optionally, in the processing method for financial product data provided in the embodiment of the present application, translating the keyword information according to a preset word list, and obtaining a first translation result of a target language corresponding to the keyword information includes: translating the keyword information according to a preset word list to obtain an initial translation result; and acquiring a first correction result of the initial translation result, and updating the initial translation result according to the first correction result to obtain the first translation result.

For example, the keyword information in the product specification of the target financial product is translated in a target language by traversing a preset common vocabulary to obtain a corresponding translation result (i.e., the initial translation result) in the common vocabulary, then a proofreading result (i.e., the first proofreading result) of the corresponding translation result in the common vocabulary is obtained, and the corresponding translation result in the common vocabulary is updated according to the obtained proofreading result to obtain a final keyword translation result.

Because the content of the keyword information in the specification of the financial product is relatively fixed, the keyword information can be rapidly translated through the common word list, then the corresponding translation result in the common word list is checked, the check result is obtained, the accuracy of keyword information translation is ensured, and the processing efficiency of the data information of the target financial product is improved.

Optionally, in the processing method of financial product data provided in the embodiment of the present application, obtaining a target translation result of a target language corresponding to product information includes: carrying out sentence splitting on the product information of the target financial product to obtain a plurality of split sentences; processing the multiple split sentences through a first machine translation model to obtain second translation results of target languages corresponding to the multiple split sentences; combining the second translation results of the target languages corresponding to the divided sentences to obtain a third translation result; and obtaining a second correction result of a third translation result, and updating the third translation result according to the second correction result to obtain the target translation result.

For example, sentence splitting is performed on sentences in a product specification of a target financial product to obtain a plurality of short sentences (i.e., the split sentences), batch translation is performed on the plurality of short sentences through a machine translation model (i.e., the first machine translation model) to obtain translation results (i.e., the second translation results) of the plurality of short sentences output by the machine translation model, then the translation results of the plurality of short sentences are combined to obtain a preliminary translation result (i.e., the third translation results) of the product specification, then the preliminary translation results of the product specification are collated to obtain a collation result (i.e., the second collation result) of the preliminary translation result of the product specification, and the preliminary translation result of the product specification is updated according to the collation result of the product specification to determine a final translation result (i.e., the target translation result) of the product specification.

The method has the advantages that firstly, through carrying out sentence splitting on sentences in the product specification, longer sentences are prevented from being translated through the machine translation model, the accuracy of the machine translation model in translating the product specification is guaranteed, then, the preliminary translation result of the product specification output by the machine translation model is checked, the translation result of the checked product specification is enabled to be more in line with the reading habit of a customer, and the translation accuracy of the product specification is further improved.

Optionally, in the processing method of financial product data provided in the embodiment of the present application, obtaining the second correction result for the third translation result includes: acquiring first historical click volume data of a target financial product and second historical click volume data of a financial product of a non-target financial product; determining a verification order of product information of the target financial product according to the first historical click quantity data and the second historical click quantity data; and according to the checking order, checking the third translation result to obtain a second checking result of the third translation result.

For example, historical click volume data of a target financial product and historical click volume data of financial products except the target financial product in a service page are obtained, a checking order of product specifications of the target financial product is determined according to the size of the historical click volume data, and a translation result output by a machine translation model is checked according to the determined checking order, so that a checking result of the translation result output by the machine translation model is obtained.

It should be noted that, there may be a plurality of financial products in the service page, so the machine translation model may need to translate the product specifications of a plurality of financial products at the same time, which may cause a situation that the translation results output by the machine translation model of the product specifications of a plurality of financial products need to be checked.

When determining the order of checking the product information of the target financial product, the issue time of the target financial product needs to be considered, and when the difference between the click rate data of the two financial products is smaller than a threshold value (for example, 100), the product specification translation result of the financial product with the early issue time is checked preferentially.

According to the historical click quantity data of a plurality of financial products, the verification order of the translation results output by the machine translation model of the product specification of the target financial product is determined, and the translation results output by the machine translation model are verified according to the verification order, so that timeliness of verifying the translation results output by the machine translation model is ensured.

Optionally, in the method for processing financial product data provided in the embodiment of the present application, after updating the third translation result according to the second calibration result to obtain the target translation result, the method further includes: determining a positive sample set according to product information of the target financial product and the target translation result; determining a negative sample set according to the product information of the target financial product and the third translation result; training the first machine translation model through the positive sample set and the negative sample set to obtain a second machine translation model; judging whether to update the first machine translation model according to the second machine translation model to obtain a target judgment result; and if the target judgment result represents that the first machine translation model is updated, updating the second machine translation model into the first machine translation model.

For example, a positive sample set is determined according to the product specification text of the target financial product and the translation result of the product specification after calibration, a negative sample set is determined according to the product specification text of the target financial product and the translation result output by the machine translation model, then the machine translation model is trained through the positive sample set and the negative sample set to obtain a trained machine translation model (namely the second machine translation model), and whether the machine translation model is updated or not is judged according to the trained machine translation model to obtain a target judgment result. If the target judgment result indicates that the machine translation model is updated, replacing the machine translation model with the trained machine translation model to update the existing machine translation model.

The machine translation model after training is obtained by training the existing machine translation model, and whether the machine translation model is updated or not is judged according to the machine translation model after training, so that the translation accuracy of the machine translation model is ensured.

Optionally, in the method for processing financial product data provided in the embodiment of the present application, determining, according to the second machine translation model, whether to update the first machine translation model, to obtain the target determination result includes: obtaining a test sample set, wherein the test sample set at least comprises product information of a plurality of financial products and real translation results of target languages corresponding to the information of each financial product; translating the product information of the financial products in the test sample set through the first machine translation model to obtain a fourth translation result; translating the product information of the financial products in the test sample set through a second machine translation model to obtain a fifth translation result; calculating a first translation accuracy corresponding to a fourth translation result according to the real translation result; calculating a second translation accuracy corresponding to the fifth translation result according to the real translation result; and judging whether to update the first machine translation model according to the first translation accuracy and the second translation accuracy to obtain a target judgment result.

For example, a test sample set is obtained first, the test sample set includes product specifications of a plurality of financial products and real translation results of each specification, then the plurality of product specifications in the test sample set are translated through a machine translation model to obtain a fourth translation result, and the plurality of product specifications in the test sample set are translated through a trained machine translation model to obtain a fifth translation result. And respectively calculating the translation accuracy of the fourth translation result and the translation accuracy of the fifth translation result by taking the real translation result as a standard to obtain a first translation accuracy corresponding to the fourth translation result and a second translation accuracy corresponding to the fifth translation result, namely, the first translation accuracy of the machine translation model and the second translation accuracy of the trained machine translation model, and judging whether to update the machine translation model according to the first translation accuracy and the second translation accuracy to obtain a target judgment result.

And testing the machine translation model and the trained machine translation model through the test sample set, calculating the first translation accuracy of the machine translation model to the test sample set and the second translation accuracy of the trained machine translation model to the test sample set, quantifying the translation effect of the machine translation model, judging whether to update the machine translation model according to the translation effects of the two machine translation models, and ensuring the translation accuracy of the machine translation model.

Optionally, in the method for processing financial product data provided in the embodiment of the present application, determining whether to update the first machine translation model according to the first translation accuracy and the second translation accuracy, to obtain the target determination result includes: judging whether the second translation accuracy is greater than the first translation accuracy; if the second translation accuracy is greater than the first translation accuracy, determining that the target judgment result is that the first machine translation model is updated; and if the second translation accuracy is smaller than or equal to the first translation accuracy, determining that the target judgment result is that the first machine translation model is not updated.

For example, judging whether the second translation accuracy of the trained machine translation model is greater than the first translation accuracy of the machine translation model, if the second translation accuracy is greater than the first translation accuracy, then proving that the translation effect of the trained machine translation model is better than that of the machine translation model, and updating the machine translation model; if the second translation accuracy is smaller than or equal to the first translation accuracy, the translation effect of the trained machine translation model is proved to be not better than that of the machine translation model, and the machine translation model is not updated.

And comparing the first translation accuracy with the second translation accuracy to determine whether the translation effect of the trained machine translation model is better than that of the machine translation model, and updating the machine translation model under the condition that the translation effect of the trained machine translation model is better than that of the machine translation model, so that the translation accuracy of the machine translation model is improved.

In an alternative embodiment, the processing method of the financial product data is implemented through the flowchart shown in fig. 2, and specific steps are as follows: step 201, obtaining product keyword information of a target financial product; step 202, translating the keyword information according to the common word list to obtain an initial translation result, and pushing the initial translation result to a financial product service page; step 203, checking the initial translation result to obtain a checking result, and updating the initial translation result according to the checking result; step 204, receiving a selection instruction of a user for a translation result corresponding to the keyword information in the financial product service page; step 205, judging whether to translate the product specification of the target financial product in full text according to the selection instruction of the user, if yes, proceeding to step 206, otherwise ending the translation flow; step 206, splitting sentences from the product specification of the target financial product to obtain a plurality of short sentences; step 207, translating the plurality of short sentences through a machine translation model to obtain translation results of the plurality of short sentences, and merging the plurality of short sentences into the translation results of the product specification; step 208, obtaining click quantity data of all financial products in the financial product service page, and determining a verification sequence of the translation result of the product specification of the target financial product according to the click quantity data; step 209, proofreading the translation result of the product specification of the target financial product according to the proofreading order, and updating the translation result of the product specification of the target financial product according to the proofreading result; step 210, training the machine translation model according to the product specification, the translation result and the correction result of the product specification to obtain a trained machine translation model; step 211, comparing the translation effect of the machine translation model with that of the trained machine translation model, and determining the machine translation model with better translation effect as the machine translation model for translating the product instruction book next time.

According to the processing method of the financial product data, the keyword information in the product information of the target financial product is obtained, wherein the keyword information comprises at least one of the following: product name, product type, product deadline, and risk information for the target financial product; translating the keyword information according to a preset word list to obtain a first translation result of a target language corresponding to the keyword information; pushing the first translation result and the keyword information to a target object, and judging whether a selection instruction of the target object on the first translation result is received or not; if a selection instruction is received, acquiring product information of a target financial product and acquiring a target translation result of a target language corresponding to the product information; the product information and the target translation result are pushed to the target object, so that the problem that the data processing efficiency is low due to the fact that a large amount of system resources are occupied because the whole introduction information of the financial product is directly translated and displayed in bilingual mode in the related technology is solved. In the application, the keyword information of the target financial product is translated firstly, the translation result of the keyword information is pushed to the target object, then whether the complete product information of the target financial product is translated or not is determined according to the selection information of the target object on the keyword result, the direct full-text translation of the product information of the financial product is avoided, and the effect of improving the processing efficiency of the data information of the financial product is achieved.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.

The embodiment of the application also provides a processing device for the financial product data, and it should be noted that the processing device for the financial product data in the embodiment of the application can be used for executing the processing method for the financial product data provided in the embodiment of the application. The following describes a processing device for financial product data provided in an embodiment of the present application.

Fig. 3 is a schematic diagram of a processing device for financial product data according to an embodiment of the present application. As shown in fig. 3, the apparatus includes: a first acquisition unit 301, a translation unit 302, a first pushing unit 303, a second acquisition unit 304, and a second pushing unit 305.

A first obtaining unit 301, configured to obtain keyword information in product information of a target financial product, where the keyword information includes at least one of the following: product name, product type, product deadline, and risk information for the target financial product;

The translation unit 302 is configured to translate the keyword information according to a preset vocabulary, so as to obtain a first translation result of the target language corresponding to the keyword information;

a first pushing unit 303, configured to push the first translation result and the keyword information to the target object, and determine whether a selection instruction of the target object for the first translation result is received;

the second obtaining unit 304 is configured to obtain product information of a target financial product and a target translation result of a target language corresponding to the obtained product information if the selection instruction is received;

and a second pushing unit 305, configured to push the product information and the target translation result to the target object.

The processing device for financial product data provided in the embodiment of the present application acquires, through the first acquiring unit 301, keyword information in product information of a target financial product, where the keyword information includes at least one of the following: product name, product type, product deadline, and risk information for the target financial product; the translation unit 302 translates the keyword information according to a preset word list to obtain a first translation result of the target language corresponding to the keyword information; the first pushing unit 303 pushes the first translation result and the keyword information to the target object, and determines whether a selection instruction of the target object for the first translation result is received; if the second obtaining unit 304 receives the selection instruction, obtaining product information of the target financial product and obtaining a target translation result of a target language corresponding to the product information; the second pushing unit 305 pushes the product information and the target translation result to the target object, so that the problem that the data processing efficiency is low due to occupation of a large amount of system resources caused by direct bilingual translation and display of the complete introduction information of the financial product in the related art is solved. In the application, the keyword information of the target financial product is translated firstly, the translation result of the keyword information is pushed to the target object, then whether the complete product information of the target financial product is translated or not is determined according to the selection information of the target object on the keyword result, the direct full-text translation of the product information of the financial product is avoided, and the effect of improving the processing efficiency of the data information of the financial product is achieved.

Optionally, in the processing apparatus for financial product data provided in the embodiment of the present application, the translation unit 302 includes: the first translation module is used for translating the keyword information according to a preset word list to obtain an initial translation result; the first acquisition module is used for acquiring a first correction result of the initial translation result, and updating the initial translation result according to the first correction result to obtain the first translation result.

Optionally, in the processing apparatus for financial product data provided in the embodiment of the present application, the second obtaining unit 304 includes: the splitting module is used for splitting the product information of the target financial product to obtain a plurality of split sentences; the processing module is used for processing the plurality of split sentences through the first machine translation model to obtain second translation results of target languages corresponding to the plurality of split sentences; the merging module is used for merging the second translation results of the target languages corresponding to the split sentences to obtain a third translation result; the second obtaining module is used for obtaining a second correction result of a third translation result, and updating the third translation result according to the second correction result to obtain the target translation result.

Optionally, in the processing device for financial product data provided in the embodiment of the present application, the second obtaining module includes: the acquisition sub-module is used for acquiring first historical click rate data of the target financial product and second historical click rate data of financial products of non-target financial products; the determining submodule is used for determining the correction sequence of the product information of the target financial product according to the first historical click quantity data and the second historical click quantity data; and the checking sub-module is used for checking the third translation result according to the checking order to obtain a second checking result of the third translation result.

Optionally, in the processing device for financial product data provided in the embodiment of the present application, the device further includes: the first determining unit is used for determining a positive sample set according to the product information of the target financial product and the target translation result; the second determining unit is used for determining a negative sample set according to the product information of the target financial product and the third translation result; the training unit is used for training the first machine translation model through the positive sample set and the negative sample set to obtain a second machine translation model; the judging unit is used for judging whether the first machine translation model is updated according to the second machine translation model to obtain a target judging result; and the updating unit is used for updating the second machine translation model into the first machine translation model if the target judgment result represents that the first machine translation model is updated.

Optionally, in the processing device for financial product data provided in the embodiment of the present application, the determining unit includes: the third acquisition module is used for acquiring a test sample set, wherein the test sample set at least comprises product information of a plurality of financial products and real translation results of target languages corresponding to the information of each financial product; the second translation module is used for translating the product information of the financial products in the test sample set through the first machine translation model to obtain a fourth translation result; the third translation module is used for translating the product information of the financial products in the test sample set through the second machine translation model to obtain a fifth translation result; the first calculation module is used for calculating a first translation accuracy rate corresponding to the fourth translation result according to the real translation result; the second calculation module is used for calculating a second translation accuracy rate corresponding to the fifth translation result according to the real translation result; and the judging module is used for judging whether the first machine translation model is updated according to the first translation accuracy and the second translation accuracy to obtain a target judging result.

Optionally, in the processing device for financial product data provided in the embodiment of the present application, the judging module includes: the judging submodule is used for judging whether the second translation accuracy rate is larger than the first translation accuracy rate or not; the first determination submodule is used for determining that the target judgment result is to update the first machine translation model if the second translation accuracy is greater than the first translation accuracy; and the second determination submodule is used for determining that the target judgment result is that the first machine translation model is not updated if the second translation accuracy is smaller than or equal to the first translation accuracy.

The processing device for financial product data includes a processor and a memory, where the units such as the first acquiring unit 301, the translating unit 302, the first pushing unit 303, the second acquiring unit 304, and the second pushing unit 305 are stored as program units, and the processor executes the program units stored in the memory to implement corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the problem that the data processing efficiency is low due to the fact that a large amount of system resources are occupied as the kernel parameters are adjusted to directly conduct bilingual translation and display on the complete introduction information of the financial product in the related technology is solved.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the invention provides a computer readable storage medium having a program stored thereon, which when executed by a processor, implements a method of processing financial product data.

The embodiment of the invention provides a processor, which is used for running a program, wherein the processing method of financial product data is executed when the program runs.

As shown in fig. 4, an embodiment of the present invention provides an electronic device, where the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, the following steps are implemented: obtaining keyword information in product information of a target financial product, wherein the keyword information comprises at least one of the following components: product name, product type, product deadline, and risk information for the target financial product; translating the keyword information according to a preset word list to obtain a first translation result of a target language corresponding to the keyword information; pushing the first translation result and the keyword information to a target object, and judging whether a selection instruction of the target object on the first translation result is received or not; if a selection instruction is received, acquiring product information of a target financial product and acquiring a target translation result of a target language corresponding to the product information; and pushing the product information and the target translation result to the target object.

Optionally, in the method for processing financial product data provided in the embodiment of the present application, determining whether to update the first machine translation model according to the first translation accuracy and the second translation accuracy, to obtain the target determination result includes: judging whether the second translation accuracy is greater than the first translation accuracy; if the second translation accuracy is greater than the first translation accuracy, determining that the target judgment result is that the first machine translation model is updated; and if the second translation accuracy is smaller than or equal to the first translation accuracy, determining that the target judgment result is that the first machine translation model is not updated. The device herein may be a server, PC, PAD, cell phone, etc.

The present application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: obtaining keyword information in product information of a target financial product, wherein the keyword information comprises at least one of the following components: product name, product type, product deadline, and risk information for the target financial product; translating the keyword information according to a preset word list to obtain a first translation result of a target language corresponding to the keyword information; pushing the first translation result and the keyword information to a target object, and judging whether a selection instruction of the target object on the first translation result is received or not; if a selection instruction is received, acquiring product information of a target financial product and acquiring a target translation result of a target language corresponding to the product information; and pushing the product information and the target translation result to the target object.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A method of processing financial product data, comprising:

obtaining keyword information in product information of a target financial product, wherein the keyword information comprises at least one of the following components: product name, product type, product period and risk information of the target financial product;

Translating the keyword information according to a preset word list to obtain a first translation result of a target language corresponding to the keyword information;

pushing the first translation result and the keyword information to a target object, and judging whether a selection instruction of the target object on the first translation result is received or not;

if the selection instruction is received, acquiring product information of the target financial product and acquiring a target translation result of a target language corresponding to the product information;

pushing the product information and the target translation result to the target object.

2. The method of claim 1, wherein translating the keyword information according to a preset vocabulary to obtain a first translation result of a target language corresponding to the keyword information comprises:

translating the keyword information according to a preset word list to obtain an initial translation result;

and acquiring a first correction result of the initial translation result, and updating the initial translation result according to the first correction result to obtain the first translation result.

3. The method of claim 1, wherein obtaining a target translation result of a target language corresponding to the product information comprises:

Carrying out sentence splitting on the product information of the target financial product to obtain a plurality of split sentences;

processing the multiple split sentences through a first machine translation model to obtain second translation results of target languages corresponding to the multiple split sentences;

combining the second translation results of the target languages corresponding to the divided sentences to obtain a third translation result;

and obtaining a second correction result of the third translation result, and updating the third translation result according to the second correction result to obtain the target translation result.

4. The method of claim 3, wherein obtaining a second correction result to the third translation result comprises:

acquiring first historical click volume data of the target financial product and second historical click volume data of financial products of non-target financial products;

determining a verification order of product information of the target financial product according to the first historical click quantity data and the second historical click quantity data;

and according to the proofreading order, proofreading the third translation result to obtain a second proofreading result of the third translation result.

5. A method according to claim 3, wherein after updating the third translation result in accordance with the second collation result to obtain the target translation result, the method further comprises:

determining a positive sample set according to the product information of the target financial product and the target translation result;

determining a negative sample set according to the product information of the target financial product and the third translation result;

training the first machine translation model through the positive sample set and the negative sample set to obtain a second machine translation model;

judging whether to update the first machine translation model according to the second machine translation model to obtain a target judgment result;

and if the target judgment result characterization updates the first machine translation model, updating the second machine translation model into the first machine translation model.

6. The method of claim 5, wherein determining whether to update the first machine translation model based on the second machine translation model comprises:

obtaining a test sample set, wherein the test sample set at least comprises product information of a plurality of financial products and real translation results of target languages corresponding to the financial product information;

Translating the product information of the financial products in the test sample set through the first machine translation model to obtain a fourth translation result;

translating the product information of the financial products in the test sample set through the second machine translation model to obtain a fifth translation result;

calculating a first translation accuracy corresponding to the fourth translation result according to the real translation result;

calculating a second translation accuracy corresponding to the fifth translation result according to the real translation result;

and judging whether to update the first machine translation model according to the first translation accuracy and the second translation accuracy to obtain the target judgment result.

7. The method of claim 6, wherein determining whether to update the first machine translation model based on the first translation accuracy and the second translation accuracy, the target determination result comprising:

judging whether the second translation accuracy rate is greater than the first translation accuracy rate;

if the second translation accuracy is greater than the first translation accuracy, determining that the target judgment result is that the first machine translation model is updated;

And if the second translation accuracy is smaller than or equal to the first translation accuracy, determining that the target judgment result is that the first machine translation model is not updated.

8. A financial product data processing apparatus, comprising:

a first obtaining unit, configured to obtain keyword information in product information of a target financial product, where the keyword information includes at least one of the following: product name, product type, product period and risk information of the target financial product;

the translation unit is used for translating the keyword information according to a preset word list to obtain a first translation result of a target language corresponding to the keyword information;

the first pushing unit is used for pushing the first translation result and the keyword information to a target object and judging whether a selection instruction of the target object on the first translation result is received or not;

the second obtaining unit is used for obtaining the product information of the target financial product and obtaining a target translation result of a target language corresponding to the product information if the selection instruction is received;

and the second pushing unit is used for pushing the product information and the target translation result to the target object.

9. A computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored program, wherein the program, when run, controls the storage medium to execute the method of processing financial product data according to any one of claims 1 to 7 at a device.

10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of processing financial product data of any of claims 1 to 7.