Data processing method, device, equipment and storage medium based on interest rate data

Abstract

The embodiment of the present invention provides a data processing method, device, equipment and storage medium based on interest rate data. The method includes: receiving a request for generating a daily interest rate report triggered by a user; in response to the request for generating a daily interest rate report, obtaining original interest rate data and a target text template sentence corresponding to at least one section, where the section is an interest rate related section; performing text differentiation processing on the target text template sentence to obtain a semantically consistent target transformation text sentence; determining the corresponding indicator value according to the target text template sentence and the original interest rate data of each section; generating a target interest rate report according to the indicator value of each section and the corresponding target transformation text sentence. The expression style of the text content of each daily interest rate report can be different, and the content is more flexible and varied, which is suitable for people's reading habits. And it can realize the automatic generation of the daily interest rate report by the electronic device, thereby improving the generation efficiency of the daily interest rate report.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of data processing technology, and in particular, to a data processing method, device, equipment and storage medium based on interest rate data. Background Art

[0002] With the development of mobile Internet, people get more information from various applications. In the financial field, the daily interest rate report is an important means for people to understand the daily interest rate situation.

[0003] In the prior art, when generating a daily interest rate report, the editor of the daily interest rate report generally imports the interest rate data into a table of Excel office software first, and then uses various functions in the Excel office software to analyze the imported interest rate data to obtain indicator values, and then fills the indicator values ​​into the corresponding target text template statement to form the final daily interest rate report.

[0004] Therefore, the interest rate daily report generation method in the prior art generates the text content of the interest rate daily report by filling in the indicator values ​​into the target text template sentence, resulting in the expression style of the text content of each interest rate daily report being very similar, the content being not flexible enough, and not suitable for people's reading habits. In addition, the generation process of the interest rate daily report requires manual participation, which is time-consuming and labor-intensive, resulting in low efficiency in the generation of the interest rate daily report. Summary of the invention

[0005] The embodiments of the present invention provide a data processing method, device, equipment and storage medium based on interest rate data, so as to solve the technical problems in the prior art that the expression style of the text content of each daily interest rate report is very similar, the content is not flexible enough and is not suitable for people's reading habits, and the generation process of the daily interest rate report requires manual participation, which is time-consuming and labor-intensive, resulting in low generation efficiency of the daily interest rate report.

[0006] In a first aspect, an embodiment of the present invention provides a data method based on interest rate data, comprising:

[0007] Receive a user-triggered request to generate a daily interest rate report;

[0008] In response to the interest rate daily report generation request, obtaining original interest rate data and target text template statements corresponding to at least one section, wherein the section is an interest rate related section;

[0009] Performing text differentiation processing on the target text template sentence to obtain a semantically consistent target transformed text sentence;

[0010] Determine the corresponding indicator value based on the target text template statements and original interest rate data of each section;

[0011] Generate a daily target interest rate report based on the indicator values ​​of each section and the corresponding target transformation text statements.

[0012] In a second aspect, an embodiment of the present invention provides a data processing device based on interest rate data, comprising:

[0013] A receiving module, used for receiving a request for generating a daily interest rate report triggered by a user;

[0014] An acquisition module, configured to acquire original interest rate data and a target text template statement corresponding to at least one section in response to the interest rate daily report generation request, wherein the section is an interest rate related section;

[0015] A text processing module, used for performing text differentiation processing on the target text template sentence to obtain a semantically consistent target transformed text sentence;

[0016] A determination module, used to determine the corresponding indicator value according to the target text template statement and the original interest rate data of each section;

[0017] The generation module is used to generate a daily target interest rate report based on the indicator values ​​of each section and the corresponding target transformation text statements.

[0018] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: at least one processor, a memory and an input device;

[0019] The processor, the memory and the input device are interconnected via a circuit;

[0020] The memory stores computer-executable instructions; the input device is used to receive a request triggered by a user;

[0021] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the method according to the first aspect.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0023] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0024] The data processing method, device, equipment and storage medium based on interest rate data provided by the embodiment of the present invention receive a user-triggered interest rate daily report generation request; in response to the interest rate daily report generation request, obtain the original interest rate data and target text template sentence corresponding to at least one section; perform text differentiation processing on the target text template sentence to obtain a semantically consistent target transformation text sentence; determine the corresponding index value according to the target text template sentence and the original interest rate data of each section; generate a target interest rate daily report according to the index value of each section and the corresponding target transformation text sentence. Since after the text differentiation processing is performed on the target text template sentence of each section, the expression mode of the target transformation text sentence is obviously different from the target text template sentence but the semantics are consistent, and each time the text differentiation processing is performed on the target text template sentence, the semantically consistent target transformation text sentence obtained each time can also be different, so the expression style of the text content of each interest rate daily report is different, the content is more flexible and changeable, and suitable for people's reading habits. And it can realize the automatic generation of interest rate daily reports by electronic equipment, thereby improving the generation efficiency of interest rate daily reports. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0026] Figure 1 This is an application scenario diagram that can implement the data processing method based on interest rate data of an embodiment of the present invention;

[0027] Figure 2 It is a flowchart of a data processing method based on interest rate data provided by an embodiment of the present invention;

[0028] Figure 3 is a flow chart of a data processing method based on interest rate data provided by another embodiment of the present invention;

[0029] Figure 4 It is a schematic diagram of a target interest rate daily report in a data processing method based on interest rate data provided by an embodiment of the present invention;

[0030] Figure 5 This is a schematic diagram of an operation interface of a data processing method based on interest rate data provided by an embodiment of the present invention;

[0031] Figure 6 is a flow chart of a data processing method based on interest rate data provided by another embodiment of the present invention;

[0032] Figure 7 is a flow chart of a data processing method based on interest rate data provided by yet another embodiment of the present invention;

[0033] Figure 8 It is another schematic diagram of an operation interface of a data processing method based on interest rate data provided by an embodiment of the present invention;

[0034] Fig. 9 is a schematic diagram of the structure of a data processing device based on interest rate data provided by an embodiment of the present invention;

[0035] Fig.10 is a schematic diagram of the structure of a data processing device based on interest rate data provided by another embodiment of the present invention;

[0036] Fig.11 is a first block diagram of an electronic device for implementing a data processing method based on interest rate data according to an embodiment of the present invention;

[0037] Fig.12 This is a second block diagram of an electronic device used to implement the data processing method based on interest rate data according to an embodiment of the present invention.

[0038] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0039] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0040] In order to clearly understand the technical solution of the present application, the solution of the prior art is first introduced in detail.

[0041] In the prior art, when generating a daily interest rate report, the editor of the daily interest rate report generally generates the daily interest rate report through the functions of the Excel office software and the target text template statement. Specifically, the editor of the daily interest rate report imports the original interest rate data into the Excel table, analyzes the original interest rate data in the Excel table, such as sorting the original interest rate input, performing sum operations, difference operations, etc., and calculates the value of the index data. Then, the value of the index data is manually filled into the target text template statement to form the daily interest rate report, and the daily interest rate report is published after checking that it is correct.

[0042] Therefore, the interest rate daily report generation method in the prior art generates the text content in the interest rate daily report by filling the indicator value into the target text template sentence. However, the interest rate daily report is a service provided to people every day, so the expression style of the text content of the interest rate daily report provided every day is very similar, the content is not flexible enough, and it is not suitable for people's reading habits. In addition, the generation process of the interest rate daily report requires manual participation, which is time-consuming and labor-intensive, making the generation efficiency of the interest rate daily report low.

[0043] Therefore, in view of the technical problems in the prior art that the text content of the daily interest rate report provided every day is very similar in expression style, the content is not flexible enough, and it is not suitable for people's reading habits, the inventor found in the research that in order to make the content of the daily interest rate report provided every day more flexible and suitable for people's reading habits, natural language processing can be performed on the target text template sentence in the text content to determine the semantics of the target text template sentence, and then the target text template sentence can be text-differentiated according to the semantics to convert the target text template sentence into a text sentence with other expressions that are consistent in semantics. Then, the daily interest rate report is generated according to the converted text sentence.

[0044] In view of the technical problem that the generation process of the interest rate daily report in the prior art requires manual participation, is time-consuming and labor-intensive, and makes the generation efficiency of the interest rate daily report low, the inventors have found in their research that the generation process of the interest rate daily report with manual participation can be transformed into a process in which the electronic device automatically generates the interest rate daily report. That is, after receiving the interest rate daily report generation request triggered by the user, the original interest rate data and the target text template statement are automatically obtained from the database or external server, and then the target text template statement is subjected to text differentiation processing to obtain a semantically consistent target transformation text statement. Then, the corresponding indicator value is determined according to the target text template statement and the original interest rate data, and the target interest rate daily report is generated according to the indicator value and the corresponding target transformation text statement. The automatic generation of the interest rate daily report by the electronic device can be realized, thereby improving the generation efficiency of the interest rate daily report.

[0045] Therefore, based on the above creative findings, the inventors have proposed a technical solution of the embodiment of the present invention. The application scenario of the data processing method based on interest rate data provided by the embodiment of the present invention is introduced below.

[0046] like Figure 1As shown, the application scenario corresponding to the data processing method based on interest rate data provided by the embodiment of the present invention may include an electronic device 1 and a database or an external server 2. Among them, the original interest rate data is stored in the database or the external server 2. The application of the data processing method based on interest rate data of the present invention is installed in the electronic device 1. The application can interact with the user through a web page or a client. The electronic device 1 communicates with the database or the external server 2 and accesses the original interest rate data in the database or the external server at any time. When the user, that is, the editor of the interest rate daily report, needs to generate the interest rate daily report every day, the web page or client of the application can be opened through the electronic device 1, and the interest rate daily report generation request can be triggered by clicking the link of "automatic generation of interest rate daily report" in the preset operation interface of the web page or the client. After receiving the interest rate daily report generation request, the electronic device 1 can obtain the original interest rate data corresponding to at least one section included in the interest rate daily report on that day from the database or the external server 2. And the target text template sentence can be obtained locally from the electronic device 1. First, the target text template sentence corresponding to each section is subjected to text differentiation processing to obtain each target transformation text sentence that is semantically consistent with the target text template sentence. Then, the corresponding index value is determined according to the target text template sentence of each section and the original interest rate data, and the target interest rate daily report is generated according to the index value of each section and the corresponding target transformation text sentence. Since after the text differentiation processing of the target text template sentence of each section, the expression of the target transformation text sentence is obviously different from the target text template sentence but the semantics are consistent, and each time the text differentiation processing of the target text template sentence is performed, the semantically consistent target transformation text sentence obtained each time can also be different, so the expression style of the text content of each interest rate daily report is different, the content is more flexible and changeable, and suitable for people's reading habits. And it can realize the automatic generation of interest rate daily reports by electronic devices, thereby improving the generation efficiency of interest rate daily reports.

[0047] The following specific embodiments are used to describe in detail the technical solutions of the present invention and how the technical solutions of the present application solve the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0048] Embodiment 1

[0049] Figure 2 is a flow chart of a data processing method based on interest rate data provided by an embodiment of the present invention, such as Figure 2As shown, the execution subject of the embodiment of the present invention is a data processing device based on interest rate data, which can be integrated in an electronic device, and the electronic device can be a computer, a server, a server cluster or other devices with independent computing and processing capabilities. The data processing method based on interest rate data provided in this embodiment includes the following steps.

[0050] Step 101: Receive a request for generating a daily interest rate report triggered by a user.

[0051] In this embodiment, the user can open the web page or client of the application of the data processing method based on interest rate data of the present invention installed in the electronic device, and click the link of "automatically generate daily interest rate report" in the preset operation interface of the web page or client to trigger the request for generating daily interest rate report.

[0052] The interest rate daily report generation request may also include: date information of the day, so as to automatically generate the interest rate daily report of the day according to the current date information.

[0053] Step 102, in response to a request to generate a daily interest rate report, obtain original interest rate data and a target text template statement corresponding to at least one section.

[0054] Among them, the section is the interest rate related section.

[0055] In this embodiment, the section information included in the daily interest rate report can be pre-configured, such as the sections included in the daily interest rate report include the money market section, interest rate conversion section, interest rate bond market section, credit bond market section, foreign exchange market section, etc.

[0056] In this embodiment, after receiving the interest rate daily report generation request, in response to the interest rate daily report generation request, the original interest rate data corresponding to each section is obtained from the database or external server. The target text template sentence of each section can be stored locally in advance, and the target text template sentence of each section can be obtained locally.

[0057] Among them, when obtaining the original interest rate data corresponding to each section from the database or external server, an original interest rate acquisition request is sent to the database or external server, and the section identification information is included in the original interest rate acquisition request, so that the database or external server obtains the original interest rate data corresponding to the section identification information according to the original interest rate acquisition request.

[0058] The raw interest rate data may vary depending on the type of each section. Here is an example of raw interest rate data: In the foreign exchange market section, raw interest rate data may include: the exchange rate of one currency against another currency for N consecutive days, and the index of one currency for N consecutive days.

[0059] Similarly, the target text template statements will be different depending on the type of section.

[0060] Step 103: Perform text differentiation processing on the target text template sentence to obtain a semantically consistent target transformed text sentence.

[0061] Among them, text differentiation processing is a processing method for converting a sentence into multiple sentences with the same semantics but different specific texts.

[0062] In this embodiment, when performing text differentiation processing on the target text template sentence to obtain a semantically consistent target transformation text sentence, natural language processing technology can be used to perform semantic analysis on the target text template sentence, and based on the semantic analysis result, a semantically consistent sentence is obtained from a pre-stored sentence set as the target transformation text sentence.

[0063] Alternatively, in this embodiment, the target text template sentence can be input into a deep learning model, and the target text template sentence can be subjected to text differentiation processing through the deep learning model to output a semantically consistent target transformed text sentence.

[0064] In this embodiment, the manner of performing text differentiation processing on the target text template sentence is not limited.

[0065] It should be noted that each time the target text template sentence is subjected to text differentiation processing to obtain a semantically consistent target transformed text sentence, the characters in each obtained target transformed text sentence are not completely the same. Alternatively, after the target text template sentence is subjected to text differentiation processing, multiple semantically consistent transformed text sentences can be obtained, and one of the multiple semantically consistent transformed text sentences is selected as the target transformed text sentence according to the selection strategy.

[0066] Step 104, determining the corresponding indicator value according to the target text template statement of each section and the original interest rate data.

[0067] In this embodiment, the mapping relationship between the target text template statement of each section and the indicators and original interest rate data can be pre-configured. Therefore, the original interest rate data corresponding to the target text template statement of each section can be determined based on the pre-configured mapping relationship between the target text template statement of each section and the original interest rate data. Then, based on the mapping relationship between the original interest rate data and the indicators, the corresponding indicators can be determined through the corresponding original interest rate data, and the corresponding indicator values ​​can be calculated.

[0068] It is understandable that the corresponding indicator value may be determined according to the target text template statements and original interest rate data of each section in other ways, which is not limited in the present embodiment.

[0069] Step 105, generating a daily target interest rate report based on the indicator values ​​of each section and the corresponding target transformation text statements.

[0070] In this embodiment, the indicator values ​​of each section are added to the target transformation text statement to generate the target daily report text corresponding to each section, and then the target daily report texts of each section are spliced ​​to generate the target interest rate daily report.

[0071] The data processing method based on interest rate data provided in this embodiment receives a user-triggered interest rate daily report generation request; in response to the interest rate daily report generation request, obtains the original interest rate data and target text template sentence corresponding to at least one section; performs text differentiation processing on the target text template sentence to obtain a semantically consistent target transformation text sentence; determines the corresponding index value according to the target text template sentence and the original interest rate data of each section; generates a target interest rate daily report according to the index value of each section and the corresponding target transformation text sentence. Since after the text differentiation processing is performed on the target text template sentence of each section, the expression mode of the target transformation text sentence is obviously different from the target text template sentence but the semantics are consistent, and each time the text differentiation processing is performed on the target text template sentence, the semantically consistent target transformation text sentence obtained each time can also be different, so the expression style of the text content of each interest rate daily report is different, the content is more flexible and changeable, and suitable for people's reading habits. And it can realize the automatic generation of interest rate daily reports by electronic equipment, thereby improving the generation efficiency of interest rate daily reports.

[0072] Embodiment 2

[0073] Figure 3 is a flow chart of a data processing method based on interest rate data provided by another embodiment of the present invention, such as Figure 3 As shown, the data processing method based on interest rate data provided in this embodiment is based on the data processing method based on interest rate data provided in the first embodiment of the present invention, and further refines step 103 to step 105, and also includes other steps. The data processing method based on interest rate data provided in this embodiment includes the following steps:

[0074] Step 201, receiving a request for generating a daily interest rate report triggered by a user.

[0075] Step 202, in response to a request to generate a daily interest rate report, obtain original interest rate data and a target text template statement corresponding to at least one section.

[0076] Among them, the section is the interest rate related section.

[0077] In this embodiment, the implementation of step 201-step 202 is similar to the implementation of step 101-step 102 in the first embodiment of the present invention, and will not be described in detail here.

[0078] Step 203: input the target text template sentence into the deep learning model trained to convergence, perform text differentiation processing on the target text template sentence through the deep learning model trained to convergence, and output a semantically consistent target transformed text sentence.

[0079] In this embodiment, the deep learning model may be an adversarial neural network model. Then the deep learning model trained to convergence is a generator in the adversarial neural network model trained to convergence.

[0080] In this embodiment, the target text template sentence is input into the generator in the adversarial neural network model trained to convergence, and the generator performs text differentiation processing on the target text model sentence, that is, the target text model sentence is first encoded by word vectors, and then the encoded data is converted to convert the target text model sentence into a semantically consistent target transformed text sentence.

[0081] Among them, in order to ensure that the target transformed text semantics is the same as the target text template sentence after each text differentiation processing of the target text template sentence, but the specific text is not exactly the same, there can be multiple transformed text sentences with consistent output semantics, and one of them is selected as the target transformed text sentence according to the preset selection strategy.

[0082] It is understandable that before the generator in the adversarial neural network model is first used to determine the target transformed text sentence, the adversarial neural network model needs to be trained. That is, before step 203, the step of training the adversarial neural network model is also included, which specifically includes steps 202-3a to 202-3c.

[0083] Step 202-3a, obtaining training samples corresponding to the adversarial neural network model, the training samples including: sample text template sentences and corresponding multiple sample transformation text sentences.

[0084] Among them, in each training sample, the sample text template sentence and the corresponding multiple sample transformation text sentences are all text sentences related to each section of the interest rate daily report, and the sample text template sentence and the corresponding multiple sample transformation texts in each training sample are semantically consistent, but the specific text is not exactly the same.

[0085] Step 202-3b, input the sample text template sentence into the generator of the adversarial neural network model so that the generator generates a test text sentence based on the sample text template sentence, input the test text sentence and the corresponding multiple sample transformation text sentences into the discriminator of the adversarial neural network model so that the discriminator judges the authenticity of the test text sentence, and determines the loss function based on the authenticity judgment result of the test text sentence.

[0086] In this embodiment, the adversarial neural network model includes a generator and a discriminator. The function of the generator is to generate a test text sentence based on the sample text template sentence, and the function of the discriminator is to perform authenticity judgment on the test text sentence based on the sample transformation text sentence. The loss function is determined based on the authenticity judgment result of the test text sentence.

[0087] Among them, the loss function has the expression of the test text sentence and the sample transformation text sentence.

[0088] Step 202-3c, during the process of adjusting the training parameters in the generator and the discriminator, if the loss function reaches the minimum, it is determined that the generator and the discriminator are trained to convergence to obtain an adversarial neural network model trained to convergence.

[0089] In this embodiment, the difference between the test text sentence and the sample transformation text sentence in the loss function is minimized by continuously adjusting the training parameters in the generator and the discriminator, that is, the loss function is minimized. If the probability of the discriminator's authenticity judgment result for the test text sentence is close to 0.5, it means that the generator and the discriminator have reached convergence at this time, and a generator trained to convergence and a discriminator trained to convergence are obtained. The generator trained to convergence and the discriminator trained to convergence constitute an adversarial neural network model trained to convergence.

[0090] Step 204, determining the corresponding indicator value according to the target text template statement of each section and the original interest rate data.

[0091] As an optional implementation, in this embodiment, step 204 includes the following steps:

[0092] Step 2041 , determining the indicator corresponding to the target text template statement of each section according to the target text template statement of each section and the mapping relationship between the pre-configured target text template statement and the indicator.

[0093] In this embodiment, the mapping relationship between the target text template statement and the indicator of each section is pre-configured, so the indicator in each section that has a mapping relationship with the target text template statement can be determined as the indicator corresponding to the target text template statement based on the target text section statement of each section and the mapping relationship.

[0094] Step 2042, extracting target interest rate data matching the corresponding indicator from the original interest rate data.

[0095] In this embodiment, the mapping relationship between the indicator corresponding to the target text template statement in each section and the original interest rate data is also configured in advance. Therefore, the original interest rate data matching the corresponding indicator can be extracted from the original interest rate data as the target interest rate data according to the mapping relationship.

[0096] Step 2043, according to the functional relationship between the pre-configured indicator and the target interest rate data, the target interest rate data is input into the corresponding function to calculate the corresponding indicator value.

[0097] In this embodiment, when the mapping relationship between the indicator corresponding to the target text template statement in each section and the original interest rate data is preconfigured, the functional relationship between the indicator and the original interest rate data is also configured. Therefore, the target interest rate data can be input into the corresponding function, and the corresponding indicator value can be calculated through the corresponding function.

[0098] Steps 2041 to 2043 are described as examples. For example, in the foreign exchange market section, if the target text template statement is "the basis point change of currency A against currency B compared with the previous trading day", the corresponding indicator is determined to be "basis point change", and the corresponding original interest rate data is: "basis point of the previous trading day" and "basis point of the current trading day", and the corresponding function is the difference between the basis point of the current trading day and the basis point of the previous trading day. If the difference between the basis point of the current trading day and the basis point of the previous trading day is a positive number, the final indicator value is an increase of N basis points. If the difference between the basis point of the current trading day and the basis point of the previous trading day is a negative number, the final indicator value is a decrease of N basis points.

[0099] Step 205, adding the indicator value of each section to the corresponding target transformation text sentence to generate the target daily report text corresponding to each section.

[0100] As an optional implementation, in this embodiment, step 205 includes the following steps:

[0101] Step 2051, determining the position to add the indicator value in each target transformation text sentence.

[0102] In this embodiment, the indicator value adding position in each target text template sentence can be pre-configured. Before the target text template sentence is subjected to text differentiation processing, the indicator value adding position can be marked. After the target text template sentence is subjected to text differentiation processing, the indicator value adding position in the target transformation text sentence can be determined based on semantics.

[0103] Step 2052, adding the indicator value to the corresponding indicator value adding position to generate the target daily report text corresponding to each section.

[0104] Step 206, concatenate the target daily report texts to generate the target interest rate daily report.

[0105] In this embodiment, when the target daily report texts are spliced, the target daily report texts corresponding to the blocks can be spliced ​​in paragraphs according to the pre-configured order of the blocks, and the spliced ​​texts are determined as the target interest rate daily report.

[0106] It should be noted that, in order to enable people to have a more detailed understanding of the interest rate, a daily chart can be inserted into the daily target interest rate report, so this embodiment also includes steps 210 to 213.

[0107] Step 207, generate the original daily chart corresponding to each section according to the original interest rate data of each section, perform semantic analysis on the target daily text corresponding to each section, optimize the original daily chart according to the semantic analysis result to obtain the target daily chart, and add the target daily chart corresponding to each section to the target interest rate daily report.

[0108] In this embodiment, the original interest rate data of each section is obtained, and the original interest rate data is added to the corresponding preset table to form the original daily report table of each section. The original interest rate data of each section can also be obtained, and the meaning of the coordinate axis in the figure and the position of each point in the coordinate axis are determined according to the original interest rate data, and a curve chart is drawn according to the position of each point, and the drawn curve chart is the original daily report chart.

[0109] In this embodiment, after semantic analysis of the target daily text corresponding to each section, the semantics expressed by the target daily text is determined, the data that needs to be highlighted is determined based on the semantics expressed by the target daily text, and the original daily chart is optimized to obtain a daily chart that highlights the data. The daily chart that highlights the data is the target daily chart.

[0110] For example, after semantic analysis of the target daily report text, it is determined that the interest rate changes significantly in a certain time period, and the interest rate curve of the time period can be intercepted and enlarged to obtain the target daily report graph. The data of the time period in the target daily report table is highlighted or displayed in bold font to obtain the target daily report table.

[0111] In this embodiment, Figure 4 As shown, the target daily chart corresponding to each section can be added below the corresponding target daily text to form the final target interest rate daily report.

[0112] Step 208: Display the target interest rate daily in the preset operation interface.

[0113] like Figure 5 As shown, the target interest rate daily report is displayed in the preset operation interface. It is understandable that the preset operation interface may also include an "edit" icon, and the user may check the generated target interest rate daily report. If an error is found, the target interest rate daily report may be modified by clicking the "edit" icon.

[0114] It should be noted that the preset operation interface may also include a "Save" icon. By clicking the "Save" icon, the latest changed content can be saved to the current user account. The page will automatically refresh and the latest version after saving will be displayed under "Saved Drafts" on the right side of the page. The content is not public and cannot be viewed by other website users. A list of "Saved Drafts" can be displayed on the right side of the preset operation interface. The saved draft list only saves two versions of the day, namely, all the latest drafts of the interest rate daily report and the automatically generated original version. Only two versions of the drafts saved every day are displayed: 1) the automatically generated original version 2) the latest version saved by the user on the same day. The draft file in the saved draft page can be named "Interest Rate Daily (modified)-year-month-day". For example, if the user saves the interest rate daily report on November 1, 2019, the file name is "Interest Rate Daily (modified)-2019-11-1". Similarly, the title of the automatically generated original version is named "Interest Rate Daily-2019-11-1". When you click on a saved draft, the page will automatically refresh and jump to the editing page of the interest rate daily report.

[0115] Step 209: If a target interest rate daily report publishing request is received from a user in a preset operation interface, the target interest rate daily report is published.

[0116] In this embodiment, Figure 5 As shown, the preset operation interface also includes a "publish" icon. After the user has checked the target interest rate daily report and found it to be correct, he can click the publish icon to trigger a target interest rate daily report publication request. The electronic device responds to the target interest rate daily report publication request and publishes the target interest rate daily report.

[0117] It should be noted that the preset operation interface may also include a "preview" icon. After the user clicks the "preview" icon, the published target interest rate daily report is previewed to view the effect of the target interest rate daily report after publication.

[0118] The data processing method based on interest rate data provided in this embodiment performs text differentiation processing on a target text template sentence to obtain a semantically consistent target transformation text sentence. The target text template sentence is input into a deep learning model trained to convergence, and text differentiation processing is performed on the target text template sentence by the deep learning model trained to convergence, and a semantically consistent target transformation text sentence is output. The deep learning model trained to convergence is a generator in an adversarial neural network model trained to convergence, and when the adversarial neural network model is trained, there are multiple sample transformation text sentences in the training samples. Therefore, when the target transformation text sentence is generated by the adversarial neural network model trained to convergence, the diversity of the target transformation text sentence can be guaranteed, so as to ensure that each time the target text template sentence is subjected to text differentiation processing, the semantically consistent target transformation text sentence obtained each time can be different.

[0119] The data processing method based on interest rate data provided in this embodiment generates a target interest rate daily report, generates an original daily chart corresponding to each section according to the original interest rate data of each section, performs semantic analysis on the target daily text corresponding to each section, optimizes the original daily chart according to the semantic analysis result to obtain a target daily chart, adds the target daily chart corresponding to each section to the target interest rate daily report, and can highlight the key data in the original interest rate data with the target daily chart, thereby improving the readability of the interest rate daily report for users.

[0120] Embodiment 3

[0121] Figure 6 is a flow chart of a data processing method based on interest rate data provided by another embodiment of the present invention, such as Figure 6 As shown, the data processing method based on interest rate data provided in this embodiment includes other steps on the basis of the data processing method based on interest rate data provided in Embodiment 1 or Embodiment 2 of the present invention. The data processing method based on interest rate data provided in this embodiment includes the following steps:

[0122] Step 301: receiving a request for viewing a daily historical interest rate report triggered by a user in a preset operation interface, wherein the request for viewing a daily historical interest rate report includes information on the time when the daily historical interest rate report was generated.

[0123] In this embodiment, Figure 5 As shown, the preset operation interface also includes a selection box for the interest rate daily report generation time, and the default displayed date is today's date. The user can click the selection box to select the interest rate daily report generation time. If the selected interest rate daily report generation time is before the current time and the Enter key is clicked, it means that the user has triggered a request to view the historical interest rate daily report.

[0124] Step 302, obtaining the historical interest rate daily report corresponding to the historical interest rate daily report generation time information.

[0125] In this embodiment, after the target interest rate daily report is generated every day, the target interest rate daily report is stored locally or in a database or an external server. Then, in response to the historical interest rate daily report viewing request, the historical interest rate daily report corresponding to the historical interest rate daily report generation time information is obtained.

[0126] Step 303: Display the historical interest rate daily report in a preset operation interface.

[0127] In this embodiment, the interest rate report of the day may be overlaid in the area displaying the interest rate report of the day, and the historical interest rate reports may be displayed so that the user can view the historical interest rate reports.

[0128] It can be understood that the historical interest rate daily report is an automatically generated historical interest rate daily report.

[0129] The data processing method based on interest rate data provided in the present embodiment receives a request for viewing a historical interest rate report triggered by a user in a preset operation interface, the request for viewing a historical interest rate report includes information on the time when a historical interest rate report was generated, obtains a historical interest rate report corresponding to the time when the historical interest rate report was generated, and displays the historical interest rate report in the preset operation interface, so that the user can view the interest rate report automatically generated in the past at any time, thereby providing convenience for the user to view the interest rate report.

[0130] Embodiment 4

[0131] Figure 7 is a flow chart of a data processing method based on interest rate data provided by another embodiment of the present invention, such as Figure 7 As shown, the data processing method based on interest rate data provided in this embodiment includes other steps on the basis of the data processing method based on interest rate data provided in embodiments 1 to 3 of the present invention. The data processing method based on interest rate data provided in this embodiment includes the following steps:

[0132] Step 401: receiving a target interest rate daily upload request triggered by a user in a preset operation interface.

[0133] In this embodiment, the user can edit and publish the automatically generated target interest rate report in the interest rate report display area in the preset operation interface, or copy and paste the interest rate report content in the display area into a Word document for editing. Figure 8 As shown, another preset operation interface may include an icon of "upload daily interest rate report", and the user triggers a target interest rate report upload request by clicking the icon of "upload daily interest rate report".

[0134] Step 402: In response to the target interest rate daily upload request, the uploaded target interest rate daily report is obtained.

[0135] After the user clicks the "Upload Daily Interest Rate" icon, a window for uploading the daily interest rate report may be displayed in response to the target daily interest rate upload request. The user may select a save path for the daily interest rate report to enable the electronic device to obtain the uploaded target daily interest rate report.

[0136] Step 403: Publish the uploaded daily target interest rate report and overwrite the published daily target interest rate report.

[0137] In this embodiment, if the user first clicks the "Publish" icon on the automatically generated page, and then uploads another target interest rate daily report through the "Upload Interest Rate Daily Report" icon, the electronic device recognizes that these two target interest rate daily reports are the same interest rate daily report, and the uploaded target interest rate daily report will be published, overwriting the published target interest rate daily report.

[0138] It should be noted that if a user first uploads another target interest rate daily report through the "Upload interest rate daily report" icon, and then tries to publish the automatically generated target interest rate daily report on the same day, when the user clicks the "Publish" icon, a prompt bar will automatically pop up in the operation interface, showing "This content is repeated with the uploaded target interest rate daily report. If you publish it again, it will directly overwrite the uploaded content. Do you want to continue?" There are two options below the prompt bar, namely "Cancel" and "Confirm". If the user clicks "Cancel", the prompt bar disappears and directly returns to the interest rate daily report generation page; if the user clicks "Confirm", the automatically generated target interest rate daily report will directly overwrite the uploaded target interest rate daily report.

[0139] The data processing method based on interest rate data provided in the present embodiment receives a target interest rate daily report upload request triggered by a user in a preset operation interface, responds to the target interest rate daily report upload request, obtains the uploaded target interest rate daily report, publishes the uploaded target interest rate daily report, and overwrites the published target interest rate daily report, and can promptly use the target interest rate daily report with a modified upload path to remedy the situation after the automatically generated target interest rate daily report has been published but an error is found.

[0140] Embodiment 5

[0141] Fig. 9 is a schematic diagram of the structure of a data processing device based on interest rate data provided by an embodiment of the present invention. Fig. 9 As shown, the data processing device 50 based on interest rate data provided in this embodiment includes: a receiving module 51, an acquisition module 52, a text processing module 53, a determination module 54 and a generation module 55.

[0142] Among them, the receiving module 51 is used to receive a request for generating a daily interest rate report triggered by a user. The obtaining module 52 is used to obtain the original interest rate data and the target text template sentence corresponding to at least one section in response to the request for generating a daily interest rate report, and the section is an interest rate related section. The text processing module 53 is used to perform text differentiation processing on the target text template sentence to obtain a semantically consistent target transformation text sentence. The determining module 54 is used to determine the corresponding indicator value according to the target text template sentence and the original interest rate data of each section. The generating module 55 is used to generate a target interest rate report according to the indicator value of each section and the corresponding target transformation text sentence.

[0143] The data processing device based on interest rate data provided in this embodiment can execute Figure 2 The technical solution of the method embodiment shown in the figure has the same implementation principle and technical effect as Figure 2 The method embodiments shown are similar and will not be described in detail here.

[0144] Embodiment 6

[0145] Fig.10 is a schematic diagram of the structure of a data processing device based on interest rate data provided by another embodiment of the present invention. Fig.10 As shown, the data processing device 60 based on interest rate data provided in this embodiment is based on the data processing device 50 based on interest rate data provided in Example 5, and further includes: a training module 61, a chart processing module 62, a display module 63, and a publishing module 64.

[0146] Optionally, the text processing module 53 is specifically used to:

[0147] The target text template sentence is input into the deep learning model trained to convergence; the target text template sentence is subjected to text differentiation processing by the deep learning model trained to convergence, and a semantically consistent target transformed text sentence is output.

[0148] Optionally, the deep learning model trained to convergence is a generator in an adversarial neural network model trained to convergence. Accordingly, the training module 61 is used to:

[0149] Obtain training samples corresponding to the adversarial neural network model, the training samples include: a sample text template sentence and a corresponding plurality of sample transformed text sentences; input the sample text template sentence into the generator of the adversarial neural network model so that the generator generates a test text sentence according to the sample text template sentence, input the test text sentence and the corresponding plurality of sample transformed text sentences into the discriminator of the adversarial neural network model so that the discriminator judges the authenticity of the test text sentence, and determine the loss function according to the authenticity judgment result of the test text sentence; in the process of adjusting the training parameters in the generator and the discriminator, if the loss function reaches the minimum, it is determined that the generator and the discriminator are trained to convergence, so as to obtain the adversarial neural network model trained to convergence.

[0150] Optionally, the determination module 54 is specifically configured to:

[0151] Determine the indicator corresponding to the target text template statement of each section according to the target text template statement of each section and the mapping relationship between the pre-configured target text template statement and the indicator; extract the target interest rate data matching the corresponding indicator from the original interest rate data; input the target interest rate data into the corresponding function according to the functional relationship between the pre-configured indicator and the target interest rate data to calculate the corresponding indicator value.

[0152] Optionally, the generating module 55 is specifically configured to:

[0153] Add the indicator values ​​of each section to the corresponding target transformation text statement to generate the target daily report text corresponding to each section; splice the target daily report texts to generate the target interest rate daily report.

[0154] Optionally, the generating module 55, when adding the indicator value of each section to the corresponding target transformation text sentence to generate the target daily report text corresponding to each section, is specifically used to:

[0155] Determine the indicator value adding position in each target transformation text statement; add the indicator value to the corresponding indicator value adding position to generate the target daily report text corresponding to each section.

[0156] Optionally, the chart processing module 62 is used to generate an original daily chart corresponding to each section based on the original interest rate data of each section; perform semantic analysis on the target daily text corresponding to each section; optimize the original daily chart based on the semantic analysis result to obtain a target daily chart; and add the target daily chart corresponding to each section to the target interest rate daily report.

[0157] Optionally, the display module 63 is used to display the target interest rate daily report in a preset operation interface. The publishing module 64 is used to publish the target interest rate daily report if a target interest rate daily report publishing request triggered by a user in the preset operation interface is received.

[0158] Optionally, the receiving module 51 is further used to receive a request for viewing a historical interest rate report triggered by a user in a preset operation interface, wherein the request for viewing a historical interest rate report includes information on the time when the historical interest rate report was generated. The acquiring module 52 is further used to acquire a historical interest rate report corresponding to the time when the historical interest rate report was generated. The display module 63 is further used to display the historical interest rate report in the preset operation interface.

[0159] Optionally, the receiving module 51 is further used to receive a target interest rate daily upload request triggered by a user in a preset operation interface. The obtaining module 52 is further used to respond to the target interest rate daily upload request and obtain the uploaded target interest rate daily report. The publishing module 64 is further used to publish the uploaded target interest rate daily report and overwrite the published target interest rate daily report.

[0160] The data processing device based on interest rate data provided in this embodiment can execute Figure 3 , Figure 6 and Figure 7 The technical solution of the method embodiment shown in the figure has the same implementation principle and technical effect as Figure 3 , Figure 6 and Figure 7 The method embodiments shown are similar and will not be described in detail here.

[0161] Embodiment 7

[0162] Fig.11 is a first block diagram of an electronic device for implementing a data processing method based on interest rate data according to an embodiment of the present invention, such as Fig.11 As shown, the electronic device 70 includes: a memory 71, a processor 72 and an input device 73.

[0163] The processor 72, the memory 71 and the input device 73 are interconnected via circuits;

[0164] The memory 71 stores computer-executable instructions; the input device 73 is used to receive a request triggered by a user;

[0165] At least one processor 72 executes the computer-executable instructions stored in the memory, so that the at least one processor executes the methods in the above-mentioned embodiments 1 to 4.

[0166] Embodiment 8

[0167] Fig.12is a second block diagram of an electronic device for implementing the data processing method based on interest rate data according to an embodiment of the present invention, such as Fig.12 As shown, the electronic device can be a computer, a digital broadcast terminal, a message sending and receiving device, a tablet device, a personal digital assistant, a server, a server cluster, etc.

[0168] The electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0169] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0170] The memory 804 is configured to store various types of data to support operations on the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0171] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0172] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0173] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0174] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0175] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the electronic device 800, the relative positioning of components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0176] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0177] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0178] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the above instructions can be executed by the processor 820 of the electronic device 800 to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0179] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables a terminal device to execute the data processing method based on interest rate data of the above-mentioned electronic device.

[0180] In an exemplary embodiment, a computer program product is also provided, including a computer program, and the computer program is used by a processor to execute the methods in the above-mentioned embodiments 1 to 4.

[0181] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be regarded as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0182] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A data processing method based on interest rate data, characterized in that: include: Receive a user-triggered request to generate a daily interest rate report; In response to the interest rate daily report generation request, obtaining original interest rate data and target text template statements corresponding to at least one section, wherein the section is an interest rate related section; Performing text differentiation processing on the target text template sentence to obtain a target transformed text sentence with different expressions but consistent semantics; Determine the corresponding indicator value based on the target text template statements and original interest rate data of each section; Generate a daily target interest rate report based on the indicator values ​​of each section and the corresponding target transformation text statements; Determining the corresponding indicator value according to the target text template statement of each section and the original interest rate data includes: Determine the indicator corresponding to the target text template statement of each section according to the target text template statement of each section and the mapping relationship between the pre-configured target text template statement and the indicator; Extracting target interest rate data matching the corresponding index from the original interest rate data; According to the functional relationship between the pre-configured indicator and the target interest rate data, the target interest rate data is input into the corresponding function to calculate the corresponding indicator value.

2. The method according to claim 1, characterized in that The performing text differentiation processing on the target text template sentence to obtain a semantically consistent target transformed text sentence includes: Inputting the target text template sentence into a deep learning model trained to convergence; The target text template sentence is subjected to text differentiation processing by the deep learning model trained to convergence, and a semantically consistent target transformed text sentence is output.

3. The method according to claim 2, characterized in that The deep learning model trained to convergence is a generator in an adversarial neural network model trained to convergence; Before inputting the target text template sentence into the deep learning model trained to convergence, the method further includes: Acquire training samples corresponding to the adversarial neural network model, wherein the training samples include: a sample text template sentence and corresponding multiple sample transformation text sentences; Inputting the sample text template sentence into the generator of the adversarial neural network model so that the generator generates a test text sentence according to the sample text template sentence, inputting the test text sentence and the corresponding multiple sample transformed text sentences into the discriminator of the adversarial neural network model so that the discriminator judges the authenticity of the test text sentence, and determining the loss function according to the authenticity judgment result of the test text sentence; In the process of adjusting the training parameters in the generator and the discriminator, if the loss function reaches the minimum, it is determined that the generator and the discriminator are trained to convergence to obtain an adversarial neural network model trained to convergence.

4. The method according to claim 1, characterized in that: The target interest rate daily report is generated according to the indicator values ​​of each section and the corresponding target transformation text statements, including: Add the indicator values ​​of each section to the corresponding target transformation text sentence to generate the target daily report text corresponding to each section; The target daily report texts are spliced ​​together to generate the target interest rate daily report.

5. The method according to claim 4, characterized in that The step of adding the indicator values ​​of each section to the corresponding target transformation text statement to generate the target daily report text corresponding to each section includes: Determine the location to add the indicator value in each target transformation text statement; The indicator values ​​are added to the corresponding indicator value adding positions to generate the target daily report text corresponding to each section.

6. The method according to claim 4, characterized in that The method further comprises: Generate the original daily chart corresponding to each section based on the original interest rate data of each section; Perform semantic analysis on the target daily newspaper text corresponding to each section; Optimizing the original daily chart according to the semantic analysis result to obtain a target daily chart; Add the target daily chart corresponding to each section to the target interest rate daily report.

7. The method according to any one of claims 1 to 6, characterized in that: Also includes: Displaying the target interest rate daily in a preset operation interface; If a target interest rate daily report publishing request triggered by a user in a preset operation interface is received, the target interest rate daily report is published.

8. The method according to claim 7, characterized in that Also includes: Receiving a request for viewing a daily historical interest rate report triggered by a user in a preset operation interface, wherein the request for viewing a daily historical interest rate report includes information on the time when the daily historical interest rate report was generated; Obtain the historical interest rate daily report corresponding to the historical interest rate daily report generation time information; The historical interest rate daily report is displayed in a preset operation interface.

9. The method according to claim 7, characterized in that: Also includes: Receive the target interest rate daily upload request triggered by the user in the preset operation interface; In response to a target interest rate daily upload request, obtaining an uploaded target interest rate daily report; The uploaded target interest rate daily report will be published and overwrite the published target interest rate daily report.

10. A data processing device based on interest rate data, characterized in that: include: A receiving module, used to receive a user-triggered request for generating a daily interest rate report; An acquisition module, configured to acquire original interest rate data and a target text template statement corresponding to at least one section in response to the interest rate daily report generation request, wherein the section is an interest rate related section; A text processing module, used for performing text differentiation processing on the target text template sentence to obtain a target transformed text sentence with different expressions but consistent semantics; A determination module, used to determine the corresponding indicator value according to the target text template statement and the original interest rate data of each section; A generation module, used to generate a daily target interest rate report based on the indicator values ​​of each section and the corresponding target transformation text statements; The determining module is specifically used for: Determine the indicator corresponding to the target text template statement of each section according to the target text template statement of each section and the mapping relationship between the pre-configured target text template statement and the indicator; extract the target interest rate data matching the corresponding indicator from the original interest rate data; and input the target interest rate data into the corresponding function according to the functional relationship between the pre-configured indicator and the target interest rate data to calculate the corresponding indicator value.

11. The device according to claim 10, characterized in that The text processing module is specifically used for: The target text template sentence is input into a deep learning model trained to convergence; the target text template sentence is subjected to text differentiation processing by the deep learning model trained to convergence, and a semantically consistent target transformed text sentence is output.

12. The device according to claim 11, characterized in that The deep learning model trained to convergence is a generator in an adversarial neural network model trained to convergence; The device further comprises: Training modules for: Acquire training samples corresponding to the adversarial neural network model, wherein the training samples include: a sample text template sentence and a corresponding plurality of sample transformed text sentences; input the sample text template sentence into the generator of the adversarial neural network model so that the generator generates a test text sentence according to the sample text template sentence, input the test text sentence and the corresponding plurality of sample transformed text sentences into the discriminator of the adversarial neural network model so that the discriminator discriminates the authenticity of the test text sentence, and determines a loss function according to the authenticity discrimination result of the test text sentence; in the process of adjusting the training parameters in the generator and the discriminator, if the loss function reaches a minimum, determine that the generator and the discriminator are trained to convergence, so as to obtain the adversarial neural network model trained to convergence.

13. The device according to claim 10, characterized in that The generation module is specifically used for: Add the indicator values ​​of each section to the corresponding target transformation text statement to generate the target daily report text corresponding to each section; splice the target daily report texts to generate the target interest rate daily report.

14. The device according to claim 13, characterized in that The generating module, when adding the indicator value of each section to the corresponding target transformation text sentence to generate the target daily report text corresponding to each section, is specifically used to: Determine the indicator value adding position in each target transformation text sentence; add the indicator value to the corresponding indicator value adding position to generate the target daily report text corresponding to each section.

15. The device according to claim 13, characterized in that The device also includes: The chart processing module is used to generate the original daily chart corresponding to each section according to the original interest rate data of each section; perform semantic analysis on the target daily text corresponding to each section; optimize the original daily chart according to the semantic analysis result to obtain the target daily chart; add the target daily chart corresponding to each section to the target interest rate daily report.

16. The device according to any one of claims 10 to 15, characterized in that: Also includes: A display module, used to display the target interest rate daily report in a preset operation interface; The publishing module is used to publish the target interest rate daily report if a target interest rate daily report publishing request triggered by a user in a preset operation interface is received.

17. The device according to claim 16, characterized in that The receiving module is further configured to receive a request for viewing a historical interest rate report triggered by a user in a preset operation interface, wherein the request for viewing a historical interest rate report includes information on the time when the historical interest rate report was generated; The acquisition module is further used to acquire the historical interest rate daily report corresponding to the historical interest rate daily report generation time information; The display module is also used to display the historical interest rate daily report in a preset operation interface.

18. The device according to claim 16, characterized in that The receiving module is further used to receive a target interest rate daily upload request triggered by a user in a preset operation interface; The acquisition module is further used to respond to a target interest rate daily upload request and acquire the uploaded target interest rate daily report; The publishing module is further used to publish the uploaded daily target interest rate report and overwrite the published daily target interest rate report.

19. An electronic device, characterized in that: include: at least one processor, memory and input device; The processor, the memory and the input device are interconnected via a circuit; The memory stores computer-executable instructions; the input device is used to receive a request triggered by a user; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the method according to any one of claims 1 to 9.

20. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

21. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images