Compliance factor form dynamic generation method, device, equipment and storage medium

Abstract

The present invention discloses a method, device, equipment and storage medium for dynamically generating a compliance factor form. The method includes obtaining current user input data and inputting it into a user intention recognition model to obtain the current user recognition result, obtaining the corresponding current compliance factor form recommendation set based on a compliance factor form knowledge base; obtaining the target compliance factor form determined therein, and updating the target compliance factor form based on the form adjustment data; if the current form verification result of the target compliance factor form is determined to be a verification pass result, then inputting it into a pre-form generation engine to generate a visual display compliance factor form. In the embodiment of the present invention, after the current user input data is intentionally recognized, the corresponding current compliance factor form recommendation set can be quickly obtained, and after the compliance factor form is determined therefrom, a quick custom adjustment and verification are performed to automatically generate a visual form, thereby improving the flexibility and efficiency of obtaining the compliance factor form and reducing the difficulty of obtaining it.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for dynamically generating a compliance factor form. Background Art

[0002] In the financial field, trading systems such as investment trading systems and securities trading systems have been widely used, and financial institutions and enterprises need to comply with various complex regulations and compliance standards. At present, fixed form templates are often used in investment trading systems and securities trading systems. They use predefined fixed form templates to collect compliance factors, and the form content includes standardized questions, options, input types and verification rules. Fixed form templates can be either paper or electronic forms, and are usually filled out manually or submitted through an electronic form system.

[0003] Although maintaining compliance factor forms through an electronic form system improves efficiency compared to paper methods, using fixed form templates or electronic form systems also has the following disadvantages:

[0004] 1) Lack of flexibility. Fixed form templates cannot be adjusted dynamically and are difficult to adapt to changes and specific needs in different business scenarios. Whenever compliance requirements or business processes change, new forms or templates need to be redesigned and deployed, increasing the complexity of maintenance. Although the electronic form system provides a certain degree of flexibility, the form structure in the system is still relatively fixed, making it difficult to quickly respond to changes in business needs.

[0005] 2) Inefficiency. When the compliance factor form is obtained through a fixed form template or electronic form system, it relies on manual filling and processing of the form, which is prone to human errors and low efficiency. Moreover, due to the lack of dynamic adjustment capabilities, every time a compliance factor needs to be added or modified, the form needs to be redesigned and implemented from scratch, resulting in low efficiency.

[0006] 3) Difficulty in data integration and analysis. That is, data between different forms and templates is difficult to integrate, forming data silos, which hinders comprehensive and in-depth compliance analysis. Moreover, the data collection and processing process is often carried out offline, making it difficult to obtain the latest compliance status in a timely manner.

[0007] 4) Poor user convenience, that is, fixed forms and templates are usually more complicated, and it is difficult for users to obtain compliance factor forms when they are relatively lacking in professional knowledge; moreover, the form content cannot be dynamically adjusted according to the user's actual situation and input content, resulting in users having to face a large number of irrelevant or redundant options during the filling process. Summary of the invention

[0008] The embodiments of the present invention provide a method, device, equipment and storage medium for dynamically generating a compliance factor form, aiming to solve the problem that in the prior art, when setting a compliance factor form in a trading system, a fixed form template or an electronic form system is often used to determine it, resulting in poor flexibility, great difficulty and low efficiency in obtaining the compliance factor form.

[0009] In a first aspect, an embodiment of the present invention provides a method for dynamically generating a compliance factor table, which includes:

[0010] In response to a factor form generation instruction, acquiring user demand data, user usage habit data, and user attribute data corresponding to the factor form generation instruction;

[0011] Generate current user input data based on the user demand data, the user usage habit data and the user attribute data;

[0012] Obtain a pre-trained user intention recognition model, and input the current user input data into the user intention recognition model to obtain a current user recognition result;

[0013] Acquire a current compliance factor form recommendation set corresponding to the current user identification result based on a pre-built compliance factor form knowledge base; wherein the current compliance factor form recommendation set includes a plurality of current compliance factor recommendation forms;

[0014] Obtaining a target compliance factor form determined in the current compliance factor recommendation form;

[0015] If a form compliance factor adjustment instruction is detected, obtaining form adjustment data corresponding to the form compliance factor adjustment instruction, and updating the target compliance factor form accordingly based on the form adjustment data;

[0016] Verify the target compliance factor form based on a preset form verification strategy to obtain a current form verification result;

[0017] If it is determined that the current form verification result corresponds to a verification pass result, the target compliance factor form is input into a pre-built form generation engine to generate a visual display compliance factor form corresponding to the target compliance factor form.

[0018] In a second aspect, an embodiment of the present invention further provides a device for dynamically generating a compliance factor table, which includes:

[0019] A user data acquisition unit, configured to respond to a factor form generation instruction and acquire user demand data, user usage habit data and user attribute data corresponding to the factor form generation instruction;

[0020] A user input data generating unit, configured to generate current user input data based on the user demand data, the user usage habit data and the user attribute data;

[0021] A user recognition result acquisition unit, used to acquire a pre-trained user intention recognition model, and input the current user input data into the user intention recognition model to obtain a current user recognition result;

[0022] A form recommendation set acquisition unit, configured to acquire a current compliance factor form recommendation set corresponding to the current user identification result based on a pre-built compliance factor form knowledge base; wherein the current compliance factor form recommendation set includes a plurality of current compliance factor recommendation forms;

[0023] A target form acquisition unit, configured to acquire a target compliance factor form determined in the current compliance factor recommendation form;

[0024] a target form adjustment unit, configured to, if a form compliance factor adjustment instruction is detected, obtain form adjustment data corresponding to the form compliance factor adjustment instruction, and update the target compliance factor form accordingly based on the form adjustment data;

[0025] A target form verification unit, used to verify the target compliance factor form based on a preset form verification strategy to obtain a current form verification result;

[0026] The visual form generation unit is used to input the target compliance factor form into a pre-built form generation engine if it is determined that the current form verification result corresponds to a verification pass result, and generate a visual display compliance factor form corresponding to the target compliance factor form.

[0027] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0028] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method described in the first aspect above can be implemented.

[0029] The embodiment of the present invention provides a method, apparatus, device and storage medium for dynamically generating a compliance factor form, the method comprising: in response to a factor form generation instruction, obtaining user demand data, user usage habit data and user attribute data corresponding to the factor form generation instruction; generating current user input data based on the user demand data, user usage habit data and user attribute data; obtaining a pre-trained user intention recognition model, and inputting the current user input data into the user intention recognition model to obtain a current user recognition result; obtaining a current compliance factor form recommendation set corresponding to the current user recognition result based on a pre-built compliance factor form knowledge base; wherein the current compliance factor form recommendation set includes a plurality of current compliance factor recommendation forms; obtaining a target compliance factor form determined in the current compliance factor recommendation form; if a form compliance factor adjustment instruction is detected, obtaining form adjustment data corresponding to the form compliance factor adjustment instruction, and updating the target compliance factor form accordingly based on the form adjustment data; verifying the target compliance factor form based on a preset form verification strategy to obtain a current form verification result; if it is determined that the current form verification result corresponds to a verification pass result, inputting the target compliance factor form into a pre-built form generation engine to generate a visual display compliance factor form corresponding to the target compliance factor form. In the embodiment of the present invention, after the user accesses the system and obtains the current user input data for intent recognition, the corresponding current compliance factor form recommendation set can be quickly obtained, and after at least one compliance factor form is determined therefrom, a quick customized flexible adjustment and verification are performed and a visual form is automatically generated, thereby improving the flexibility and efficiency of obtaining compliance factor forms and reducing the difficulty of obtaining them. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0031] Figure 1 A schematic diagram of an application scenario of the method for dynamically generating a compliance factor form provided by an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of a flow chart of a method for dynamically generating a compliance factor table provided in an embodiment of the present invention;

[0033] Figure 3 A schematic diagram of a sub-process of a method for dynamically generating a compliance factor form provided in an embodiment of the present invention;

[0034] Figure 4A schematic diagram of another sub-process of the method for dynamically generating a compliance factor form provided by an embodiment of the present invention;

[0035] Figure 5 A schematic diagram of another sub-process of the method for dynamically generating a compliance factor form provided by an embodiment of the present invention;

[0036] Figure 6 A schematic diagram of another sub-process of the method for dynamically generating a compliance factor form provided in an embodiment of the present invention;

[0037] Figure 7 A schematic block diagram of a device for dynamically generating a compliance factor form provided by an embodiment of the present invention;

[0038] Figure 8 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0041] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0042] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0043] Please also see Figure 1 and Figure 2 , Figure 1 Schematic diagram of a scenario of a method for dynamically generating a compliance factor form according to an embodiment of the present invention. Figure 21 is a flow chart of a method for dynamically generating a compliance factor form according to an embodiment of the present invention. The method is applied to a server 10, and the server 10 can be connected to a user terminal 20 for communication. Figure 2 As shown, the method includes the following steps S110-S180.

[0044] S110 . In response to a factor form generation instruction, obtain user demand data, user usage habit data, and user attribute data corresponding to the factor form generation instruction.

[0045] In this embodiment, the technical solution is described with the server as the execution subject. A compliance factor form dynamic generation system is deployed in the server, and the user terminal can log in to the compliance factor form dynamic generation system of the server based on its registered account and password to perform the compliance factor form dynamic generation operation. For example, the technical solution of the present application can be understood by taking the application of the compliance factor form dynamic generation system to the Internet financial transaction scenario as an example. More specifically, if a financial institution has a need to verify the legality and compliance of financial transaction data, in order to verify the financial transaction data, it is necessary to pre-build or deploy a compliance factor form, and perform data verification on the financial transaction data based on the compliance factor form, thereby obtaining the compliance verification result of the transaction data.

[0046] When a user logs in to the compliance factor form dynamic generation system of the server based on his / her registered account and password, a factor form generation instruction is triggered, that is, the user's login operation is used to perform the compliance factor form dynamic generation operation. At this time, the server can obtain the user's corresponding user demand data, user usage habit data and user attribute data.

[0047] Among them, user demand data can be the text or several keywords manually entered by the user to describe the compliance factor table generation requirements, for example, the text describing the compliance factor table generation requirements is a compliance factor table for the application scenario of securities declaration number limit, or several keywords include securities trading, declaration number and upper limit, etc.; user usage habit data is a number of commonly used compliance factors of the user obtained based on the user's previous compliance factor generation history records; user attribute data at least includes the user account identity type, for example, the user account identity type is XX1 company YY1 department ordinary account, XX2 company YY2 department administrator account, etc. When the server's compliance factor table dynamic generation system obtains the user demand data, user usage habit data and user attribute data generated by the user's use of the system this time, it can be used as the initial user data for subsequent user intent analysis.

[0048] S120. Generate current user input data based on the user demand data, the user usage habit data and the user attribute data.

[0049] In this embodiment, after the user demand data, the user usage habit data and the user attribute data are obtained, the above data can be concatenated in sequence according to a preset order to obtain the current user input data.

[0050] Of course, in the specific implementation, in order to facilitate the subsequent rapid analysis of user intentions, the user demand data, the user usage habit data and the user attribute data can also be vectorized separately, and then merged to form the current user input data. For example, first obtain the semantic vector corresponding to the user demand data (first extract several keywords corresponding to the user demand data and then comprehensively determine the semantic vector from the word vectors corresponding to the several keywords); then obtain the compliance factors corresponding to the user usage habit data and the word vectors corresponding to each of them; then obtain the coding value corresponding to the user account identity type in the user attribute data (for example, the coding value corresponding to the ordinary account of the YY1 department of XX1 company is 0, and the coding value of the administrator account of the YY2 department of XX2 company is 1, etc.); finally, the semantic vector corresponding to the user demand data, the compliance factors corresponding to the user usage habit data, the word vectors corresponding to each of them, and the coding value corresponding to the user account identity type in the user attribute data are sequentially connected to obtain the column vector (which can also be a row vector) as the current user input data. It can be seen that based on the above method, the current user input data including multi-dimensional information of the user can be obtained, which can be used as input data for more accurately obtaining the compliance factors required by the user.

[0051] S130, obtaining a pre-trained user intention recognition model, and inputting the current user input data into the user intention recognition model to obtain a current user recognition result.

[0052] In this embodiment, after the current user input data is determined, the user intention recognition model that has been stored locally on the server and has been trained can also be obtained, and then the current user input data is input into the user intention recognition model to obtain the current user recognition result. It can be seen that based on the above method, the current user input data and the user intention recognition model can be combined to quickly obtain the current user recognition result.

[0053] In one embodiment, the user intention recognition model is a convolutional neural network, and step S130 includes:

[0054] A current input vector corresponding to the current user input data is obtained, and the current input vector is input into the user intention recognition model to obtain the current user recognition result.

[0055] In this embodiment, the user intention recognition model specifically adopted is a convolutional neural network. Of course, the specific implementation is not limited to a convolutional neural network, and can also be a recurrent neural network, a long short-term memory network, etc. After the current user input data is obtained and it is determined that it is already in vector form, it is directly used as the current input vector, and the current input vector is input into the user intention recognition model to obtain the current user recognition result. After the current user input data is obtained and it is determined that it is in non-vector form, the current user input data can be converted into the corresponding current input vector by referring to the processing method in the above example, and then the current input vector is input into the user intention recognition model to obtain the current user recognition result. Among them, the current user recognition result obtained can be an identification value with a value in [0, 1]. Moreover, if several identification value intervals are pre-set, and each identification value interval is respectively set with a label word vector, after determining the identification value corresponding to the current user recognition result, the current target identification value interval to which it belongs and the current target label word vector corresponding to the target identification value interval can be determined accordingly.

[0056] S140: Acquire a current compliance factor form recommendation set corresponding to the current user identification result based on a pre-built compliance factor form knowledge base.

[0057] The current compliance factor form recommendation set includes a plurality of current compliance factor recommendation forms.

[0058] In this embodiment, a compliance factor form knowledge base can be pre-built in the server, and the compliance factor form knowledge base includes multiple compliance factor forms, and each compliance factor form corresponds to at least one form application scenario identification tag. In order to more clearly understand the structure of the compliance factor form in this application, a specific compliance factor form as shown in Table 1 below is used for explanation:

[0059] Table 1

[0060]

[0061] In Table 1, the fields of the header are described as follows:

[0062] a. Factor type, which is used to define the type of form item generated corresponding to the compliance factor. It can be an input text box, date selection box, drop-down selection box, etc. The form item type definitions include integer, floating point number, enumeration, string, Boolean value, date / time;

[0063] b. Factor number, used for associated data storage and binding, and display condition judgment;

[0064] c. Factor name, which is used to generate the form display title, i.e. the specific name of the compliance factor;

[0065] d. Whether it is mandatory, used to determine whether the defined compliance factor is mandatory based on this field for verification;

[0066] e. Precision, used to control the number of decimal places of the input value according to the factor type. For example, when the factor type is floating point and the corresponding compliance factor of this factor type takes effect, control the number of decimal places of the input value;

[0067] f. Default value, used to set the initial default value display corresponding to each compliance factor when initially generating the compliance factor form;

[0068] g. Value range: When the factor type is selected as "integer" or "floating point", the value range is optional and the filling format is: use X to represent this compliance factor. If it is a < X < b, then it corresponds to (a, b) in the value range; if it is a < X ≤ b, then it corresponds to (a, b] in the value range; (3) a ≤ x < b, then it corresponds to [a, b) in the value range; (4) a ≤ x ≤ b, then it corresponds to [a, b] in the value range; when the factor type is selected as "enumeration", the value range is mandatory and the filling format is: enumeration 1: number 1: enumeration 2: number 2 (the names of enumeration 1, enumeration 2, etc. use English symbols); when the factor type is selected as "string", the value range is mandatory and fill in the length of the string, and its filling format is: a, and a means that the length of the string shall not exceed a characters;

[0069] h. Unit, which takes effect when the factor type is integer or floating point, and units such as yuan and pen can be set;

[0070] i. Display condition: Only when the display condition set by this field is met can the custom factor be displayed. For example, when adding three compliance factors a, b, and c, and setting the display condition as a = 1 && b > 4 || c = 8 when adding the compliance factor d, then the compliance factor d will only be displayed in the compliance factor form when a is equal to 1 and b is greater than 4 or c is equal to 8;

[0071] j. Factor description, used to explain the corresponding compliance factor after generating the compliance factor form.

[0072] Moreover, for the compliance factor form shown in Table 1 above (each row in Table 1 represents the detailed information of a compliance factor, and Table 1 does not fill in the specific compliance factor but only shows the table structure), at least one form application scenario identification tag is also set (such as the upper limit of the number of declarations in the above example, and it can also be the upper limit of the declaration rate, the upper limit of the number of transactions in a short period of time, etc.). After determining the current user identification result, the current compliance factor form recommendation set corresponding to the current user identification result can be obtained according to the preset matching strategy.

[0073] In one embodiment, if Figure 3 As shown, step S140 includes:

[0074] S141, obtaining a current target label word vector corresponding to the current user recognition result;

[0075] S142, obtaining a form application scenario identification label vector corresponding to each current compliance factor form in the compliance factor form knowledge base;

[0076] S143. If it is determined that the similarity between the form application scenario identification label vector of the current compliance factor form in the compliance factor form knowledge base and the current target label word vector exceeds a preset similarity threshold, the corresponding current compliance factor form is obtained to form the current compliance factor form recommendation set.

[0077] In this embodiment, after determining the current user identification result, if the current user identification result can also be converted into a user label, several form application scenario identification labels whose similarity (such as cosine similarity) with the current user identification result exceeds the preset similarity threshold can be obtained from the compliance factor form knowledge base, and their corresponding compliance factor forms. Specifically, first obtain the current target label word vector corresponding to the current user identification result, and then calculate the similarity between the current target label word vector and the form application scenario identification label vector corresponding to each current compliance factor form in the compliance factor form knowledge base, and finally filter out the current compliance factor form that satisfies the similarity between the form application scenario identification label vector and the current target label word vector exceeding the preset similarity threshold. After filtering out the above-mentioned compliance factor forms, a recommendation set of current compliance factor forms corresponding to the current user identification result can be formed.

[0078] S150: Obtain a target compliance factor form determined in the current compliance factor recommendation form.

[0079] In this embodiment, after the current compliance factor recommendation form is displayed in the form of a visual optional list, the user selects at least one current compliance factor recommendation form according to actual needs and uses it as the target compliance factor form. Of course, the obtained target compliance factor form is not the compliance factor form that the user ultimately expects, and the user can also customize some compliance factors in the target compliance factor form.

[0080] S160: If a form compliance factor adjustment instruction is detected, obtain form adjustment data corresponding to the form compliance factor adjustment instruction, and update the target compliance factor form accordingly based on the form adjustment data.

[0081] In this embodiment, if a form compliance factor adjustment instruction is detected, it means that the user has a need to adjust the target compliance factor form, such as replacing some of the compliance factors, adjusting the accuracy of the compliance factors, adjusting the display conditions of the compliance factors, adjusting the value range of the compliance factors, adjusting the units of the compliance factors, adjusting the factor descriptions of the compliance factors, etc. Afterwards, after obtaining the form adjustment data corresponding to the form compliance factor adjustment instruction, the target compliance factor form can be updated in real time. In the above manner, the user's customized modification requirements for the target compliance factor form can be received in real time and the form can be updated quickly in real time.

[0082] In one embodiment, if Figure 4 As shown, step S160 includes:

[0083] S161: If it is determined that the form adjustment data corresponds to compliance factor replacement data, then when the compliance factor replacement data satisfies a compatibility check condition with each non-replaced compliance factor in the target compliance factor form, the target compliance factor form is updated accordingly according to the compliance factor replacement data;

[0084] S162: If it is determined that the form adjustment data corresponds to the compliance factor local attribute adjustment data, then the target compliance factor form is updated accordingly according to the compliance factor local attribute adjustment data.

[0085] In this embodiment, when the target compliance factor form is updated according to the form adjustment data corresponding to the form compliance factor adjustment instruction, it is necessary to specifically analyze whether to replace the compliance factor in the target compliance factor form or to make local attribute adjustments to the existing compliance factor, so as to perform form update processing more quickly and accurately.

[0086] For example, the target compliance factor form includes 20 compliance factors and they are recorded as F1-F20 respectively. If it is determined that the form adjustment data corresponds to the compliance factor replacement data, and the compliance factors F1, F4 and F9 need to be completely deleted and replaced with other compliance factors, then the currently replaced compliance factors F1' and F4' can be obtained first, and then the compatibility check is performed on the compliance factors F1' and F4' with the remaining 17 compliance factors in the target compliance factor form, that is, it is determined whether the compliance factors F1' and F4' can coexist with the remaining 17 compliance factors in the target compliance factor form. After it is determined that the compliance factors F1' and F4' can coexist with the remaining 17 compliance factors in the target compliance factor form, the compliance factors F1', F4' and their corresponding factor specific information are filled into the target compliance factor form accordingly to update the target compliance factor form. When it is determined that compliance factor F1' and / or compliance factor F4' cannot exist simultaneously with the remaining 17 compliance factors in the target compliance factor form, the compliance factors among compliance factor F1' and compliance factor F4' that can exist simultaneously with the remaining 17 compliance factors in the target compliance factor form are obtained and updated to the target compliance factor form, and the user is prompted that there are incompatible compliance factors.

[0087] In one embodiment, if Figure 5 As shown, after step S161, the following steps are also included:

[0088] S1611. If it is determined that the form adjustment data corresponds to compliance factor replacement data, then when the compliance factor replacement data does not satisfy the compatibility verification conditions with the non-replaced compliance factors in the target compliance factor form, the compliance factors in the compliance factor replacement data that do not satisfy the compatibility verification conditions are deleted, and the target compliance factor form is updated.

[0089] In this embodiment, if it is determined that the form adjustment data corresponds to the compliance factor replacement data, then when the compliance factor replacement data does not meet the compatibility verification conditions with the non-replaced compliance factors in the target compliance factor form, it means that at least one compliance factor in the form adjustment data does not meet the compatibility verification conditions. At this time, the corresponding compliance factor can be deleted in the form adjustment data, and the target compliance factor form can be updated with the compliance factor retained in the form adjustment data. It can be seen that based on the initial verification of the above-mentioned compliance factors, the compliance factors in the compliance factor replacement data that do not meet the compatibility verification conditions can be quickly screened out, and their update to the target compliance factor form can be avoided, resulting in erroneous data in the form.

[0090] In one embodiment, if Figure 5As shown, after step S1611, the following steps are also included:

[0091] S1612: Based on a pre-built compliance factor knowledge base, obtain the compliance factors to be recommended corresponding to the compliance factors that do not meet the compatibility verification condition in the compliance factor replacement data, and fill them into the recommended factor display component for display; wherein the compliance factors to be recommended meet the compatibility verification condition;

[0092] S1613: If a replacement confirmation instruction for the compliance factor to be recommended is obtained, the target compliance factor table is updated according to the compliance factor to be recommended.

[0093] In this embodiment, a compliance factor knowledge base may be pre-built in the server, and the compliance factor knowledge base includes multiple compliance factor groups, and compliance factors belonging to the same compliance factor group have similar factor attributes (it can be understood that there are differences between the compliance factors, but the differences are small, and they can be used as replacement factors for each other). If several compliance factors to be recommended corresponding to the compliance factors in the compliance factor replacement data that do not meet the compatibility verification conditions are determined in the compliance factor knowledge base, the above several compliance factors to be recommended are filled into the recommended factor display component for display (it should be noted that the selected several compliance factors to be recommended are quickly verified with the remaining compliance factors in the target compliance factor form in the server background, and all meet the compatibility verification conditions).

[0094] Afterwards, the user can select at least one compliance factor to be recommended from the recommendation factor display component, and the compliance factor to be recommended is updated and added to the target compliance factor form. In the above manner, intelligent recommendation and replacement of compliance factors for users is achieved.

[0095] S170: Verify the target compliance factor form based on a preset form verification strategy to obtain a current form verification result.

[0096] In this embodiment, after obtaining the target compliance factor form that matches the user's needs in the server, in order to ensure its validity, the form verification strategy preset in the server can be further obtained to verify the target compliance factor form. Specifically, the form verification strategy in the form of Table 2 below can be set, which includes the verification information of all existing compliance factor types:

[0097] Table 2

[0098]

[0099] In Table 2 above, the verification information of several factor types such as integer, floating point, enumeration, string, date / time / Boolean, etc. is specifically described. For example, if the factor type of one of the compliance factors in the target compliance factor table is an integer, it is necessary to determine the maximum value judgment type and the minimum value judgment type of the compliance factor, and then determine whether the value of the compliance factor is within the corresponding value range determined by the minimum value and the maximum value, so as to complete the verification of the compliance factor.

[0100] In one embodiment, if Figure 6 As shown, step S170 includes:

[0101] S171. Obtain the factor type of each compliance factor in the target compliance factor form, and determine the corresponding target verification sub-strategy in the form verification strategy based on the factor type of each compliance factor;

[0102] S172, verifying each compliance factor in the target compliance factor table based on the corresponding target syndrome strategy, and obtaining syndrome results corresponding to each compliance factor;

[0103] S173: If it is determined that the verification sub-results corresponding to the compliance factors in the target compliance factor form are all verification pass results, then the verification result of the current form is determined to be a verification pass result.

[0104] In this embodiment, when verifying each compliance factor in the target compliance factor form in the server, the target verification sub-strategy corresponding to each compliance factor can be determined from the form verification strategy shown in Table 2 above.

[0105] Afterwards, the corresponding compliance factors are verified with the target verification sub-strategies corresponding to each compliance factor, and the verification sub-results corresponding to each compliance factor are obtained. Only when the verification sub-results corresponding to each compliance factor in the target compliance factor form are all verification pass results, the verification result of the current form is determined to be a verification pass result. As long as there is a verification sub-result corresponding to a compliance factor that fails the verification, the compliance factor can be marked in time in the target compliance factor form (such as a highlight mark) to prompt the user to adjust the compliance factor in time (such as modifying the specific value of the compliance factor so that it is within the value range determined by the corresponding minimum and maximum values). After the adjustment is completed, the adjusted compliance factor can be verified again based on the corresponding target verification sub-strategy, and after the verification passes, the verification sub-result corresponding to the compliance factor is adjusted to a verification pass result.

[0106] S180: If it is determined that the current form verification result corresponds to a verification pass result, the target compliance factor form is input into a pre-built form generation engine to generate a visual display compliance factor form corresponding to the target compliance factor form.

[0107] In this embodiment, if it is determined that the current form verification result corresponds to a verification pass result, a visual display compliance factor form can be generated based on the form generation engine. For example, an initial Form form (a form with data collection, verification and submission functions) is defined in the form generation engine. The form generation engine obtains the target compliance factor form through the interface and obtains the compliance factor data of each row in the target compliance factor form in a traversal manner and fills it into the initial Form form. In addition, in the above process, different attribute sub-components can be created for each compliance factor based on the factor type (such as drop-down options, input boxes, date and time selections, etc., specifically using vue dynamic components to introduce them into the factor items of the compliance factor). Finally, a form verification can be finally performed based on the form generation engine, and a visual display compliance factor form corresponding to the target compliance factor form can be obtained after the verification is correct.

[0108] It can be seen that the embodiment of the method can quickly obtain the corresponding current compliance factor form recommendation set after performing intent recognition based on the current user input data obtained by the user accessing the system, and automatically generate a visual form after quickly customizing and flexibly adjusting and verifying after determining at least one compliance factor form. The flexibility and efficiency of obtaining compliance factor forms are improved, and the difficulty of obtaining is reduced.

[0109] Figure 7 is a schematic block diagram of a device for dynamically generating a compliance factor form provided by an embodiment of the present invention. Figure 7 As shown, corresponding to the above compliance factor form dynamic generation method, the present invention also provides a compliance factor form dynamic generation device 100. The compliance factor form dynamic generation device 100 includes: a user data acquisition unit 110, a user input data generation unit 120, a user identification result acquisition unit 130, a form recommendation set acquisition unit 140, a target form acquisition unit 150, a target form adjustment unit 160, a target form verification unit 170 and a visual form generation unit 180.

[0110] The user data acquisition unit 110 is used to respond to the factor form generation instruction and acquire the user demand data, user usage habit data and user attribute data corresponding to the factor form generation instruction.

[0111] In this embodiment, the technical solution is described with the server as the execution subject. A compliance factor form dynamic generation system is deployed in the server, and the user terminal can log in to the compliance factor form dynamic generation system of the server based on its registered account and password to perform the compliance factor form dynamic generation operation. For example, the technical solution of the present application can be understood by taking the application of the compliance factor form dynamic generation system to the Internet financial transaction scenario as an example. More specifically, if a financial institution has a need to verify the legality and compliance of financial transaction data, in order to verify the financial transaction data, it is necessary to pre-build or deploy a compliance factor form, and perform data verification on the financial transaction data based on the compliance factor form, thereby obtaining the compliance verification result of the transaction data.

[0112] When a user logs in to the compliance factor form dynamic generation system of the server based on his / her registered account and password, a factor form generation instruction is triggered, that is, the user's login operation is used to perform the compliance factor form dynamic generation operation. At this time, the server can obtain the user's corresponding user demand data, user usage habit data and user attribute data.

[0113] Among them, user demand data can be the text or several keywords manually entered by the user to describe the compliance factor table generation requirements, for example, the text describing the compliance factor table generation requirements is a compliance factor table for the application scenario of securities declaration number limit, or several keywords include securities trading, declaration number and upper limit, etc.; user usage habit data is a number of commonly used compliance factors of the user obtained based on the user's previous compliance factor generation history records; user attribute data at least includes the user account identity type, for example, the user account identity type is XX1 company YY1 department ordinary account, XX2 company YY2 department administrator account, etc. When the server's compliance factor table dynamic generation system obtains the user demand data, user usage habit data and user attribute data generated by the user's use of the system this time, it can be used as the initial user data for subsequent user intent analysis.

[0114] The user input data generating unit 120 is used to generate current user input data based on the user demand data, the user usage habit data and the user attribute data.

[0115] In this embodiment, after the user demand data, the user usage habit data and the user attribute data are obtained, the above data can be concatenated in sequence according to a preset order to obtain the current user input data.

[0116] Of course, in the specific implementation, in order to facilitate the subsequent rapid analysis of user intentions, the user demand data, the user usage habit data and the user attribute data can also be vectorized separately, and then merged to form the current user input data. For example, first obtain the semantic vector corresponding to the user demand data (first extract several keywords corresponding to the user demand data and then comprehensively determine the semantic vector from the word vectors corresponding to the several keywords); then obtain the compliance factors corresponding to the user usage habit data and the word vectors corresponding to each of them; then obtain the coding value corresponding to the user account identity type in the user attribute data (for example, the coding value corresponding to the ordinary account of the YY1 department of XX1 company is 0, and the coding value of the administrator account of the YY2 department of XX2 company is 1, etc.); finally, the semantic vector corresponding to the user demand data, the compliance factors corresponding to the user usage habit data, the word vectors corresponding to each of them, and the coding value corresponding to the user account identity type in the user attribute data are sequentially connected to obtain the column vector (which can also be a row vector) as the current user input data. It can be seen that based on the above method, the current user input data including multi-dimensional information of the user can be obtained, which can be used as input data for more accurately obtaining the compliance factors required by the user.

[0117] The user recognition result acquisition unit 130 is used to acquire a pre-trained user intention recognition model, and input the current user input data into the user intention recognition model to obtain a current user recognition result.

[0118] In this embodiment, after the current user input data is determined, the user intention recognition model that has been stored locally on the server and has been trained can also be obtained, and then the current user input data is input into the user intention recognition model to obtain the current user recognition result. It can be seen that based on the above method, the current user input data and the user intention recognition model can be combined to quickly obtain the current user recognition result.

[0119] In one embodiment, the user intention recognition model is a convolutional neural network, and the user recognition result acquisition unit 130 is specifically used to:

[0120] A current input vector corresponding to the current user input data is obtained, and the current input vector is input into the user intention recognition model to obtain the current user recognition result.

[0121] In this embodiment, the user intention recognition model specifically adopted is a convolutional neural network. Of course, the specific implementation is not limited to a convolutional neural network, and can also be a recurrent neural network, a long short-term memory network, etc. After the current user input data is obtained and it is determined that it is already in vector form, it is directly used as the current input vector, and the current input vector is input into the user intention recognition model to obtain the current user recognition result. After the current user input data is obtained and it is determined that it is in non-vector form, the current user input data can be converted into the corresponding current input vector by referring to the processing method in the above example, and then the current input vector is input into the user intention recognition model to obtain the current user recognition result. Among them, the current user recognition result obtained can be an identification value with a value in [0, 1]. Moreover, if several identification value intervals are pre-set, and each identification value interval is respectively set with a label word vector, after determining the identification value corresponding to the current user recognition result, the current target identification value interval to which it belongs and the current target label word vector corresponding to the target identification value interval can be determined accordingly.

[0122] The form recommendation set acquisition unit 140 is configured to acquire a current compliance factor form recommendation set corresponding to the current user identification result based on a pre-built compliance factor form knowledge base.

[0123] The current compliance factor form recommendation set includes a plurality of current compliance factor recommendation forms.

[0124] In this embodiment, a compliance factor form knowledge base can be pre-built in the server, and the compliance factor form knowledge base includes multiple compliance factor forms, and each compliance factor form corresponds to at least one form application scenario identification tag. In order to more clearly understand the structure of the compliance factor form in this application, please refer to Table 1 above.

[0125] Moreover, for the compliance factor form shown in Table 1 above (each row in Table 1 represents the detailed information of a compliance factor, and Table 1 does not fill in the specific compliance factor but only shows the table structure), at least one form application scenario identification tag is also set (such as the upper limit of the number of declarations in the above example, and it can also be the upper limit of the declaration rate, the upper limit of the number of transactions in a short period of time, etc.). After determining the current user identification result, the current compliance factor form recommendation set corresponding to the current user identification result can be obtained according to the preset matching strategy.

[0126] In one embodiment, the form recommendation set acquisition unit 140 is specifically configured to:

[0127] Obtaining a current target label word vector corresponding to the current user recognition result;

[0128] Obtaining a form application scenario identification label vector corresponding to each current compliance factor form in the compliance factor form knowledge base;

[0129] If it is determined that the similarity between the form application scenario identification label vector of the current compliance factor form in the compliance factor form knowledge base and the current target label word vector exceeds a preset similarity threshold, the corresponding current compliance factor form is obtained to form the current compliance factor form recommendation set.

[0130] In this embodiment, after determining the current user identification result, if the current user identification result can also be converted into a user label, several form application scenario identification labels whose similarity (such as cosine similarity) with the current user identification result exceeds the preset similarity threshold can be obtained from the compliance factor form knowledge base, and their corresponding compliance factor forms. Specifically, first obtain the current target label word vector corresponding to the current user identification result, and then calculate the similarity between the current target label word vector and the form application scenario identification label vector corresponding to each current compliance factor form in the compliance factor form knowledge base, and finally filter out the current compliance factor form that satisfies the similarity between the form application scenario identification label vector and the current target label word vector exceeding the preset similarity threshold. After filtering out the above-mentioned compliance factor forms, a recommendation set of current compliance factor forms corresponding to the current user identification result can be formed.

[0131] The target form acquisition unit 150 is configured to acquire a target compliance factor form determined in the current compliance factor recommendation form.

[0132] In this embodiment, after the current compliance factor recommendation form is displayed in the form of a visual optional list, the user selects at least one current compliance factor recommendation form according to actual needs and uses it as the target compliance factor form. Of course, the obtained target compliance factor form is not the compliance factor form that the user ultimately expects, and the user can also customize some compliance factors in the target compliance factor form.

[0133] The target form adjustment unit 160 is configured to, if a form compliance factor adjustment instruction is detected, obtain form adjustment data corresponding to the form compliance factor adjustment instruction, and update the target compliance factor form accordingly based on the form adjustment data.

[0134] In this embodiment, if a form compliance factor adjustment instruction is detected, it means that the user has a need to adjust the target compliance factor form, such as replacing some of the compliance factors, adjusting the accuracy of the compliance factors, adjusting the display conditions of the compliance factors, adjusting the value range of the compliance factors, adjusting the units of the compliance factors, adjusting the factor descriptions of the compliance factors, etc. Afterwards, after obtaining the form adjustment data corresponding to the form compliance factor adjustment instruction, the target compliance factor form can be updated in real time. In the above manner, the user's customized modification requirements for the target compliance factor form can be received in real time and the form can be updated quickly in real time.

[0135] In one embodiment, the target form adjustment unit 160 is specifically used to:

[0136] If it is determined that the form adjustment data corresponds to compliance factor replacement data, then when the compliance factor replacement data satisfies a compatibility check condition with each non-replaced compliance factor in the target compliance factor form, the target compliance factor form is updated accordingly according to the compliance factor replacement data;

[0137] If it is determined that the form adjustment data corresponds to the compliance factor local attribute adjustment data, the target compliance factor form is updated accordingly according to the compliance factor local attribute adjustment data.

[0138] In this embodiment, when the target compliance factor form is updated according to the form adjustment data corresponding to the form compliance factor adjustment instruction, it is necessary to specifically analyze whether to replace the compliance factor in the target compliance factor form or to make local attribute adjustments to the existing compliance factor, so as to perform form update processing more quickly and accurately.

[0139] For example, the target compliance factor form includes 20 compliance factors and they are recorded as F1-F20 respectively. If it is determined that the form adjustment data corresponds to the compliance factor replacement data, and the compliance factors F1, F4 and F9 need to be completely deleted and replaced with other compliance factors, then the currently replaced compliance factors F1' and F4' can be obtained first, and then the compatibility check is performed on the compliance factors F1' and F4' with the remaining 17 compliance factors in the target compliance factor form, that is, it is determined whether the compliance factors F1' and F4' can coexist with the remaining 17 compliance factors in the target compliance factor form. After it is determined that the compliance factors F1' and F4' can coexist with the remaining 17 compliance factors in the target compliance factor form, the compliance factors F1', F4' and their corresponding factor specific information are filled into the target compliance factor form accordingly to update the target compliance factor form. When it is determined that compliance factor F1' and / or compliance factor F4' cannot exist simultaneously with the remaining 17 compliance factors in the target compliance factor form, the compliance factors among compliance factor F1' and compliance factor F4' that can exist simultaneously with the remaining 17 compliance factors in the target compliance factor form are obtained and updated to the target compliance factor form, and the user is prompted that there are incompatible compliance factors.

[0140] In one embodiment, if Figure 5 As shown, if it is determined that the form adjustment data corresponds to the compliance factor replacement data, then when the compliance factor replacement data satisfies the compatibility check condition with each non-replaced compliance factor in the target compliance factor form, after updating the target compliance factor form accordingly according to the compliance factor replacement data, it also includes:

[0141] If it is determined that the form adjustment data corresponds to compliance factor replacement data, then when the compliance factor replacement data does not satisfy the compatibility verification conditions with the non-replaced compliance factors in the target compliance factor form, the compliance factors in the compliance factor replacement data that do not satisfy the compatibility verification conditions are deleted, and the target compliance factor form is updated.

[0142] In this embodiment, if it is determined that the form adjustment data corresponds to the compliance factor replacement data, then when the compliance factor replacement data does not meet the compatibility verification conditions with the non-replaced compliance factors in the target compliance factor form, it means that at least one compliance factor in the form adjustment data does not meet the compatibility verification conditions. At this time, the corresponding compliance factor can be deleted in the form adjustment data, and the target compliance factor form can be updated with the compliance factor retained in the form adjustment data. It can be seen that based on the initial verification of the above-mentioned compliance factors, the compliance factors in the compliance factor replacement data that do not meet the compatibility verification conditions can be quickly screened out, and their update to the target compliance factor form can be avoided, resulting in erroneous data in the form.

[0143] In one embodiment, if it is determined that the form adjustment data corresponds to compliance factor replacement data, then when the compliance factor replacement data does not satisfy the compatibility check condition with each non-replaced compliance factor in the target compliance factor form, the compliance factors in the compliance factor replacement data that do not satisfy the compatibility check condition are deleted, and after the target compliance factor form is updated, the method further includes:

[0144] Based on a pre-built compliance factor knowledge base, obtain the compliance factors to be recommended corresponding to the compliance factors that do not meet the compatibility verification conditions in the compliance factor replacement data, and fill them into the recommended factor display component for display; wherein the compliance factors to be recommended meet the compatibility verification conditions;

[0145] If a replacement confirmation instruction for the compliance factor to be recommended is obtained, the target compliance factor table is updated according to the compliance factor to be recommended.

[0146] In this embodiment, a compliance factor knowledge base may be pre-built in the server, and the compliance factor knowledge base includes multiple compliance factor groups, and compliance factors belonging to the same compliance factor group have similar factor attributes (it can be understood that there are differences between the compliance factors, but the differences are small, and they can be used as replacement factors for each other). If several compliance factors to be recommended corresponding to the compliance factors in the compliance factor replacement data that do not meet the compatibility verification conditions are determined in the compliance factor knowledge base, the above several compliance factors to be recommended are filled into the recommended factor display component for display (it should be noted that the selected several compliance factors to be recommended are quickly verified with the remaining compliance factors in the target compliance factor form in the server background, and all meet the compatibility verification conditions).

[0147] Afterwards, the user can select at least one compliance factor to be recommended from the recommendation factor display component, and the compliance factor to be recommended is updated and added to the target compliance factor form. In the above manner, intelligent recommendation and replacement of compliance factors for users is achieved.

[0148] The target form verification unit 170 is used to verify the target compliance factor form based on a preset form verification strategy to obtain a current form verification result.

[0149] In this embodiment, after obtaining the target compliance factor form that matches the user's needs in the server, in order to ensure its validity, the form verification strategy preset in the server can be further obtained to verify the target compliance factor form. Specifically, a form verification strategy in the form of Table 2 above can be set, which includes verification information of all existing compliance factor types.

[0150] In Table 2 above, the verification information of several factor types such as integer, floating point, enumeration, string, date / time / Boolean, etc. is specifically described. For example, if the factor type of one of the compliance factors in the target compliance factor table is an integer, it is necessary to determine the maximum value judgment type and the minimum value judgment type of the compliance factor, and then determine whether the value of the compliance factor is within the corresponding value range determined by the minimum value and the maximum value, so as to complete the verification of the compliance factor.

[0151] In one embodiment, the target form verification unit 170 is specifically used to:

[0152] Obtaining a factor type of each compliance factor in the target compliance factor form, and determining a corresponding target verification sub-strategy in the form verification strategy based on the factor type of each compliance factor;

[0153] Verify each compliance factor in the target compliance factor table based on the corresponding target syndrome strategy to obtain syndrome results corresponding to each compliance factor;

[0154] If it is determined that the verification sub-results corresponding to the compliance factors in the target compliance factor form are all verification pass results, then the verification result of the current form is determined to be a verification pass result.

[0155] In this embodiment, when verifying each compliance factor in the target compliance factor form in the server, the target verification sub-strategy corresponding to each compliance factor can be determined from the form verification strategy shown in Table 2 above.

[0156] Afterwards, the corresponding compliance factors are verified with the target verification sub-strategies corresponding to each compliance factor, and the verification sub-results corresponding to each compliance factor are obtained. Only when the verification sub-results corresponding to each compliance factor in the target compliance factor form are all verification pass results, the verification result of the current form is determined to be a verification pass result. As long as there is a verification sub-result corresponding to a compliance factor that fails the verification, the compliance factor can be marked in time in the target compliance factor form (such as a highlight mark) to prompt the user to adjust the compliance factor in time (such as modifying the specific value of the compliance factor so that it is within the value range determined by the corresponding minimum and maximum values). After the adjustment is completed, the adjusted compliance factor can be verified again based on the corresponding target verification sub-strategy, and after the verification passes, the verification sub-result corresponding to the compliance factor is adjusted to a verification pass result.

[0157] The visual form generating unit 180 is used to input the target compliance factor form into a pre-built form generating engine to generate a visual display compliance factor form corresponding to the target compliance factor form if it is determined that the current form verification result corresponds to a verification pass result.

[0158] In this embodiment, if it is determined that the current form verification result corresponds to a verification pass result, a visual display compliance factor form can be generated based on the form generation engine. For example, an initial Form form (a form with data collection, verification and submission functions) is defined in the form generation engine. The form generation engine obtains the target compliance factor form through the interface and obtains the compliance factor data of each row in the target compliance factor form in a traversal manner and fills it into the initial Form form. In addition, in the above process, different attribute sub-components can be created for each compliance factor based on the factor type (such as drop-down options, input boxes, date and time selections, etc., specifically using vue dynamic components to introduce them into the factor items of the compliance factor). Finally, a form verification can be finally performed based on the form generation engine, and a visual display compliance factor form corresponding to the target compliance factor form can be obtained after the verification is correct.

[0159] It can be seen that the implementation example of the device can quickly obtain the corresponding current compliance factor form recommendation set after performing intent recognition based on the current user input data obtained by the user accessing the system, and automatically generate a visual form after quickly customizing and flexibly adjusting and verifying after determining at least one compliance factor form. The flexibility and efficiency of obtaining compliance factor forms are improved, and the difficulty of obtaining is reduced.

[0160] The above-mentioned compliance factor form dynamic generation device can be implemented in the form of a computer program, which can be used in the following ways: Figure 8Runs on the computer device shown.

[0161] See also Figure 8 , Figure 8 The following is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device integrates any of the compliance factor table dynamic generation devices provided by an embodiment of the present invention.

[0162] See also Figure 8 The computer device 400 includes a processor 402 , a memory and a network interface 405 connected via a system bus 401 , wherein the memory may include a storage medium 403 and an internal memory 404 .

[0163] The storage medium 403 may store an operating system 4031 and a computer program 4032. The computer program 4032 includes program instructions, and when the program instructions are executed, the processor 402 may execute the above-mentioned compliance factor form dynamic generation method.

[0164] The processor 402 is used to provide computing and control capabilities to support the operation of the entire computer device.

[0165] The internal memory 404 provides an environment for the operation of the computer program 4032 in the storage medium 403. When the computer program 4032 is executed by the processor 402, the processor 402 can execute the above-mentioned compliance factor form dynamic generation method.

[0166] The network interface 405 is used to communicate with other devices over the network. Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0167] The processor 402 is used to run a computer program 4032 stored in the memory to implement the above-mentioned method for dynamically generating a compliance factor form.

[0168] It should be understood that in the embodiment of the present invention, the processor 402 may be a central processing unit (CPU), and the processor 402 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0169] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0170] Therefore, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the above-mentioned compliance factor table dynamic generation method.

[0171] The computer-readable storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0172] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0173] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0174] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0175] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0176] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for dynamically generating a compliance factor form, characterized in that: include: In response to a factor form generation instruction, acquiring user demand data, user usage habit data, and user attribute data corresponding to the factor form generation instruction; Generate current user input data based on the user demand data, the user usage habit data and the user attribute data; Obtain a pre-trained user intention recognition model, and input the current user input data into the user intention recognition model to obtain a current user recognition result; Acquire a current compliance factor form recommendation set corresponding to the current user identification result based on a pre-built compliance factor form knowledge base; wherein the current compliance factor form recommendation set includes a plurality of current compliance factor recommendation forms; Obtaining a target compliance factor form determined in the current compliance factor recommendation form; If a form compliance factor adjustment instruction is detected, obtaining form adjustment data corresponding to the form compliance factor adjustment instruction, and updating the target compliance factor form accordingly based on the form adjustment data; Verify the target compliance factor form based on a preset form verification strategy to obtain a current form verification result; If it is determined that the current form verification result corresponds to a verification pass result, the target compliance factor form is input into a pre-built form generation engine to generate a visual display compliance factor form corresponding to the target compliance factor form; In the step of correspondingly updating the target compliance factor form based on the form adjustment data: If it is determined that the form adjustment data corresponds to the compliance factor replacement data, then when the compliance factor replacement data does not satisfy the compatibility check condition with each non-replaced compliance factor in the target compliance factor form, the compliance factors in the compliance factor replacement data that do not satisfy the compatibility check condition are deleted, and the target compliance factor form is updated; Based on a pre-built compliance factor knowledge base, obtain the compliance factors to be recommended corresponding to the compliance factors that do not meet the compatibility verification conditions in the compliance factor replacement data, and fill them into the recommended factor display component for display; wherein the compliance factors to be recommended meet the compatibility verification conditions; If a replacement confirmation instruction for the compliance factor to be recommended is obtained, the target compliance factor table is updated according to the compliance factor to be recommended.

2. The method according to claim 1, characterized in that The user intention recognition model is a convolutional neural network; the inputting the current user input data into the user intention recognition model to obtain the current user recognition result includes: A current input vector corresponding to the current user input data is obtained, and the current input vector is input into the user intention recognition model to obtain the current user recognition result.

3. The method according to claim 1, characterized in that The obtaining, based on a pre-built compliance factor form knowledge base, a current compliance factor form recommendation set corresponding to the current user identification result includes: Obtaining a current target label word vector corresponding to the current user recognition result; Obtaining a form application scenario identification label vector corresponding to each current compliance factor form in the compliance factor form knowledge base; If it is determined that the similarity between the form application scenario identification label vector of the current compliance factor form in the compliance factor form knowledge base and the current target label word vector exceeds a preset similarity threshold, the corresponding current compliance factor form is obtained to form the current compliance factor form recommendation set.

4. The method according to claim 1, characterized in that: The updating of the target compliance factor form based on the form adjustment data accordingly includes: If it is determined that the form adjustment data corresponds to compliance factor replacement data, then when the compliance factor replacement data satisfies a compatibility check condition with each non-replaced compliance factor in the target compliance factor form, the target compliance factor form is updated accordingly according to the compliance factor replacement data; If it is determined that the form adjustment data corresponds to the compliance factor local attribute adjustment data, the target compliance factor form is updated accordingly according to the compliance factor local attribute adjustment data.

5. The method according to claim 1, characterized in that The target compliance factor form is verified based on the preset form verification strategy to obtain the current form verification result, including: Obtaining a factor type of each compliance factor in the target compliance factor form, and determining a corresponding target verification sub-strategy in the form verification strategy based on the factor type of each compliance factor; Verify each compliance factor in the target compliance factor table based on the corresponding target syndrome strategy to obtain syndrome results corresponding to each compliance factor; If it is determined that the verification sub-results corresponding to the compliance factors in the target compliance factor form are all verification pass results, then the verification result of the current form is determined to be a verification pass result.

6. A device for dynamically generating a compliance factor form, characterized in that: include: A user data acquisition unit, configured to respond to a factor form generation instruction and acquire user demand data, user usage habit data and user attribute data corresponding to the factor form generation instruction; A user input data generating unit, configured to generate current user input data based on the user demand data, the user usage habit data and the user attribute data; A user recognition result acquisition unit, used to acquire a pre-trained user intention recognition model, and input the current user input data into the user intention recognition model to obtain a current user recognition result; A form recommendation set acquisition unit, configured to acquire a current compliance factor form recommendation set corresponding to the current user identification result based on a pre-built compliance factor form knowledge base; wherein the current compliance factor form recommendation set includes a plurality of current compliance factor recommendation forms; A target form acquisition unit, configured to acquire a target compliance factor form determined in the current compliance factor recommendation form; a target form adjustment unit, configured to, if a form compliance factor adjustment instruction is detected, obtain form adjustment data corresponding to the form compliance factor adjustment instruction, and update the target compliance factor form accordingly based on the form adjustment data; A target form verification unit, used to verify the target compliance factor form based on a preset form verification strategy to obtain a current form verification result; A visual form generation unit, configured to input the target compliance factor form into a pre-built form generation engine to generate a visual display compliance factor form corresponding to the target compliance factor form if it is determined that the current form verification result corresponds to a verification pass result; The target form adjustment unit is specifically used for: If it is determined that the form adjustment data corresponds to the compliance factor replacement data, then when the compliance factor replacement data does not satisfy the compatibility check condition with each non-replaced compliance factor in the target compliance factor form, the compliance factors in the compliance factor replacement data that do not satisfy the compatibility check condition are deleted, and the target compliance factor form is updated; Based on a pre-built compliance factor knowledge base, obtain the compliance factors to be recommended corresponding to the compliance factors that do not meet the compatibility verification conditions in the compliance factor replacement data, and fill them into the recommended factor display component for display; wherein the compliance factors to be recommended meet the compatibility verification conditions; If a replacement confirmation instruction for the compliance factor to be recommended is obtained, the target compliance factor table is updated according to the compliance factor to be recommended.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for dynamically generating a compliance factor form according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor, the method for dynamically generating a compliance factor form according to any one of claims 1 to 5 can be implemented.

Images