Artificial intelligence-based information entry method, apparatus, and related device

Abstract

The application relates to an artificial intelligence technology and provides an information input method and device based on artificial intelligence, a computer device and a storage medium, which comprises the following steps: when a supervision request is received, the supervision request is analyzed to obtain a plurality of target text item contents; the importance of the target text item contents is determined, and the combination order of the target text item contents is determined according to the order of the importance in descending order; the target text item contents are combined according to the combination order to obtain an initial supervision text; the target format of the initial supervision text is determined, and the initial supervision text is adjusted according to the target format to obtain a target supervision text; the target supervision text is analyzed to obtain to-be-input information item contents; the supervision type corresponding to the target supervision text and an information input preference are determined; and the to-be-input information item contents are input into a preset system according to the information input preference. The application can improve the efficiency of information input and promote the rapid development of smart cities.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to an information input method, apparatus, computer equipment and storage medium based on artificial intelligence. Background Technology

[0002] The notification, transmission, and retention of regulatory information are key aspects of the daily compliance management of financial institutions. This is especially true for large financial groups, whose numerous branches receive dozens of types of regulatory information daily, including inspection notices, requests for assistance in investigating and freezing assets, and regulatory letters—a vast and rapidly increasing volume. This regulatory information needs to be integrated, refined, and entered into the company's corresponding regulatory information platform.

[0003] In the process of implementing this application, the applicant discovered the following problems with the existing technology: In the traditional regulatory information entry process, the relevant responsible personnel of each institution and unit are dedicated to reading, sorting, refining, processing, entering and uploading regulatory information every day. On average, each piece of regulatory information takes about 30 minutes, and each branch office spends about 1 person dedicated to entering regulatory information. The efficiency of information entry is low.

[0004] Therefore, it is necessary to provide an information entry method that can improve the efficiency of information entry. Summary of the Invention

[0005] In view of the above, it is necessary to propose an information entry method, an information entry device, a computer device, and a storage medium based on artificial intelligence, which can improve the efficiency of information entry.

[0006] The first aspect of this application provides an information entry method based on artificial intelligence, the information entry method based on artificial intelligence includes:

[0007] When a regulatory request is received, the regulatory request is parsed to obtain the content of multiple target text items;

[0008] Determine the importance of each of the target text items, and determine the combination order of the target text items according to the order of decreasing importance;

[0009] The target text items are combined according to the given combination order to obtain the initial regulatory text;

[0010] Determine the target format of the initial regulatory text, and adjust the initial regulatory text according to the target format to obtain the target regulatory text;

[0011] The target regulatory text is parsed to obtain the content of the information items to be entered;

[0012] Determine the regulatory type corresponding to the target regulatory text and the information entry preference corresponding to the regulatory type;

[0013] The information to be entered is entered into the preset system according to the information entry preference.

[0014] Furthermore, in the above-described artificial intelligence-based information input method provided in the embodiments of this application, determining the importance of the content of each target text item includes:

[0015] Obtain the target text item corresponding to the content of each target text item;

[0016] Obtain the contents of multiple historical text items corresponding to each target text item, and form a historical text item content set;

[0017] Determine the preset historical input information item identifier corresponding to each historical text item content in the historical text item content set, and calculate the number of preset historical input information item identifiers to obtain the input quantity corresponding to each historical text item content.

[0018] Calculate the target input quantity corresponding to each target text item based on several input quantities;

[0019] The importance of each target text item is determined based on the target number of entries.

[0020] Furthermore, in the above-described artificial intelligence-based information entry method provided in this application embodiment, the step of adjusting the initial regulatory text according to the target format to obtain the target regulatory text includes:

[0021] Determine the initial format corresponding to the content of each target text item to obtain an initial format set;

[0022] Multiple initial formats within the initial format set are clustered to obtain several format clusters.

[0023] Determine the pre-trained format conversion model corresponding to each of the aforementioned format clusters;

[0024] The format conversion model is invoked to adjust the initial format of each target text item within the format cluster to the target format, thereby obtaining the target regulatory text.

[0025] Furthermore, in the above-described artificial intelligence-based information entry method provided in this application embodiment, the step of parsing the target regulatory text to obtain the content of the information item to be entered includes:

[0026] Obtain keywords for preset information items and determine the target location of the keywords for preset information items in the target regulatory text;

[0027] Obtain the preset data format between the preset information item keywords and the information item content in the target regulatory text;

[0028] The content at the target location is selected as the information item to be entered according to the preset data format.

[0029] Furthermore, in the above-described artificial intelligence-based information entry method provided in this application embodiment, determining the regulatory type corresponding to the target regulatory text includes:

[0030] Determine the type of pre-trained supervision to determine the model;

[0031] The regulatory type determination model is invoked to process the target regulatory text, thereby obtaining the regulatory type corresponding to the target regulatory text.

[0032] Furthermore, in the above-described artificial intelligence-based information entry method provided in this application embodiment, determining the information entry preference corresponding to the regulatory type includes:

[0033] Determine the mapping relationship between pre-set regulatory types and information entry preferences;

[0034] By traversing the mapping relationship, the information entry preferences corresponding to the regulatory type are obtained.

[0035] Furthermore, in the above-described artificial intelligence-based information entry method provided in this application embodiment, the step of entering the content of the information item to be entered into the preset system according to the information entry preference includes:

[0036] The component type and component position corresponding to the information item to be entered are determined based on the information input preference.

[0037] Construct the target component at the component location in the preset system according to the component type;

[0038] The information to be entered is entered into the target component.

[0039] A second aspect of this application also provides an information input device based on artificial intelligence, the information input device based on artificial intelligence comprising:

[0040] The request parsing module is used to parse the regulatory request when it is received, and obtain the content of multiple target text items;

[0041] The sequence determination module is used to determine the importance of each of the target text items and to determine the combination order of the target text items according to the order of decreasing importance.

[0042] The sequential combination module is used to combine the contents of the target text item according to the combination order to obtain the initial regulatory text.

[0043] The text adjustment module is used to determine the target format of the initial regulatory text and adjust the initial regulatory text according to the target format to obtain the target regulatory text;

[0044] The text parsing module is used to parse the target regulatory text to obtain the content of the information items to be entered;

[0045] The type determination module is used to determine the regulatory type corresponding to the target regulatory text and the information entry preference corresponding to the regulatory type.

[0046] The information entry module is used to enter the content of the information item to be entered into the preset system according to the information entry preference.

[0047] A third aspect of this application also provides a computer device, the computer device including a processor, the processor being configured to execute a computer program stored in a memory to implement the artificial intelligence-based information entry method as described in any of the preceding embodiments.

[0048] A fourth aspect of this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the artificial intelligence-based information entry method described in any one of the above embodiments.

[0049] The information entry method, device, computer equipment, and computer-readable storage medium based on artificial intelligence provided in this application improve information entry efficiency by parsing the target regulatory text to obtain the content of the information items to be entered and determining the information entry preferences corresponding to the target regulatory text. The information items to be entered into a preset system according to the information entry preferences are then entered. Furthermore, this application determines the combination order of target text items based on their importance, in descending order of importance, to obtain the initial regulatory text. When determining the information items to be entered, it prioritizes traversing the regulatory text with higher importance, quickly finding the information items to be entered and avoiding the long query time caused by traversing the entire initial regulatory text, further improving information entry efficiency. This application can be applied to various functional modules of smart cities, such as smart government affairs and smart transportation, including the information entry module of a smart city, promoting the rapid development of smart cities. Attached Figure Description

[0050] Figure 1 This is a flowchart of an artificial intelligence-based information entry method provided in an embodiment of this application.

[0051] Figure 2 This is a flowchart illustrating the determination of importance provided in one embodiment of this application.

[0052] Figure 3 This is a flowchart illustrating the determination of the target regulatory text provided in one embodiment of this application.

[0053] Figure 4 This is a flowchart illustrating the process of determining the content of the information item to be entered, provided in one embodiment of this application.

[0054] Figure 5 This is a structural diagram of an artificial intelligence-based information input device provided in an embodiment of this application.

[0055] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.

[0056] The following detailed description, in conjunction with the accompanying drawings, will further illustrate this application. Detailed Implementation

[0057] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0058] Numerous specific details are set forth in the following description in order to provide a full understanding of this application. The described embodiments are only some, not all, of the embodiments of this application.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0060] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0061] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0062] The information entry method based on artificial intelligence provided in this embodiment of the invention is executed by a computer device, and correspondingly, the information entry device runs in the computer device. Figure 1 This is a flowchart of an artificial intelligence-based information entry method provided in an embodiment of this application. Figure 1 As shown, the information entry method based on artificial intelligence may include the following steps. The order of these steps in the flowchart may be changed or some may be omitted depending on different needs:

[0063] S11, When a regulatory request is received, the regulatory request is parsed to obtain the content of multiple target text items.

[0064] In at least one embodiment of this application, the regulatory request refers to a request issued by a regulatory agency to assist in the execution of relevant regulatory tasks. For example, the regulatory request may be a request issued by a regulatory agency to a financial institution to assist in executing regulatory tasks such as investigating, freezing, and deducting assets, supervising labor arbitration, and supervising system complaints. The regulatory request can be output in the form of SMS, email, etc., and is not limited thereto. The target text item content refers to the content of the target text item carried in the regulatory request. The number of target text items can be one or more. Taking the regulatory request as output in the form of email as an example, the target text item can be the email title, email body, and email attachments, and the target text item content refers to the content of the email title, email body, and email attachments.

[0065] Optionally, parsing the regulatory request yields multiple target text item contents, including:

[0066] S111, determine the keywords of the text items contained in the regulatory request;

[0067] S112, traverse the pre-set correspondence between text item keywords and text item content to obtain the target text item content corresponding to the text item keywords.

[0068] The text item keywords are pre-defined keywords used to uniquely identify text items. For example, the text item keywords could be "title," "text," or "enclosure," where "title" identifies the email title, "text" identifies the email body, and "enclosure" identifies the email attachment; there are no restrictions on this. By determining the text item keywords in the regulatory request, the target text items and their content can be obtained.

[0069] S12, determine the importance of each target text item content, and determine the combination order of the target text item content according to the order of decreasing importance.

[0070] In at least one embodiment of this application, each target text item contains a corresponding level of importance, which can be set according to actual needs. For example, taking the target text item content as the content of email title, email body, and email attachments, the email body content has the highest level of importance, and the email title content has the lowest level of importance.

[0071] Combination Figure 2 This application describes the process for determining the importance of each target text item as provided in its embodiments. Optionally, determining the importance of each target text item includes:

[0072] S121, Obtain the target text item corresponding to the content of each target text item.

[0073] In one embodiment, for each target text item content, there exists a unique corresponding target text item. The target text item content contains text item keywords corresponding to the target text item, and the text item keywords include, but are not limited to, "title", "text", and "enclosure". By determining the text item keywords in the target text item content, the target text item can be obtained.

[0074] S122, obtain the contents of multiple historical text items corresponding to each target text item, and form a historical text item content set.

[0075] In one embodiment, for each target text item, there is a corresponding historical text item content, and the number of historical text item contents can be multiple, and the multiple historical text item contents corresponding to each target text item are combined into a historical text item content set.

[0076] For example, when the target text item is an email title, the historical text item content refers to the content of historical email titles. There can be multiple historical email title contents, and the email titles corresponding to different historical email title contents can be the same or different; this is not limited. When the target text item is the email body, the historical text item content refers to the content of historical email bodies. There can be multiple historical email body contents, and different historical email body contents are generally different. When the target text item is an email attachment, the historical text item content refers to the content of historical email attachments. There can be multiple historical email attachment contents, and different historical email attachment contents are generally different.

[0077] S123, determine the preset historical input information item identifier corresponding to each historical text item content in the historical text item content set, and calculate the number of preset historical input information item identifiers to obtain the input quantity corresponding to each historical text item content.

[0078] In one embodiment, the preset historical input information item identifier refers to the content that is pre-set to mark the information item content selected from the historical text item content and entered into the preset system. The preset historical input information item identifier can be a letter identifier, a number identifier, or a color identifier, and there is no limitation on it.

[0079] S124, calculate the target input quantity corresponding to each target text item based on the input quantities.

[0080] In one embodiment, the target number of entries can be obtained by averaging several of the entry counts. For example, when the target text item is the email body, it corresponds to historical text item content A, historical text item content B, and historical text item content C. Specifically, the number of preset historical entry information item identifiers selected and entered into the preset system from historical text item content A is 3, the number of preset historical entry information item identifiers selected and entered into the preset system from historical text item content B is 4, and the number of preset historical entry information item identifiers selected and entered into the preset system from historical text item content C is 2. In this case, the target number of entries for the preset historical entry information item identifiers corresponding to the email body can be an average of 3.

[0081] S125, determine the importance of the content of each target text item based on the target input quantity.

[0082] It is understood that the importance of each target text item is determined according to the decreasing order of the number of entries. That is, the more entries, the higher the importance of the target text item; the fewer entries, the lower the importance of the target text item.

[0083] S13, combine the contents of the target text items according to the combination order to obtain the initial regulatory text.

[0084] This application embodiment determines the combination order of target text items by assessing the importance of each target text item and in descending order of importance, thus obtaining an initial regulatory text. Subsequently, when determining the information items to be entered, it can prioritize traversing the regulatory text with high importance, quickly find the information items to be entered, avoid the problem of long query time caused by traversing the entire initial regulatory text, and further improve the efficiency of information entry.

[0085] S14, determine the target format of the initial regulatory text, and adjust the initial regulatory text according to the target format to obtain the target regulatory text.

[0086] In at least one embodiment of this application, the initial regulatory text contains multiple target text items, and each target text item has a corresponding initial format. Before entering information into the initial regulatory text, the initial formats of each target text item in the initial regulatory text need to be adjusted to a unified target format to obtain the target regulatory text, thereby improving the efficiency of information entry.

[0087] Combination Figure 3 This application describes the process for determining the target regulatory text provided in its embodiments. Optionally, adjusting the initial regulatory text according to the target format to obtain the target regulatory text includes:

[0088] S141, determine the initial format corresponding to the content of each target text item to obtain an initial format set.

[0089] In one embodiment, each target text item has a corresponding initial format, which may be the same or different. For example, when the target text item is an email title, the corresponding initial format is a doc text format. When the target text item is the email body, the corresponding initial format is a doc text format. When the target text item is an email attachment, the corresponding initial format includes, but is not limited to, doc text format, xls table format, pdf file format, and jpg image format.

[0090] S142, perform clustering processing on multiple initial formats within the initial format set to obtain several format clusters;

[0091] In one embodiment, when the initial formats in the initial format set are all different, when adjusting the initial format of each target text item to the target format, a format conversion model needs to be pre-trained for each initial format in the initial format set, and then the format conversion model is called to adjust the initial format of the target text item to the target format.

[0092] In one embodiment, when the initial formats in the initial format set are the same, the initial formats in the initial format set are clustered, wherein the format cluster contains at least one identical initial format.

[0093] S143, determine the pre-trained format conversion model corresponding to each of the format clusters.

[0094] In one embodiment, the input vector of the format conversion model is the text item content in the initial format, and the output vector is the text item content in the target format. The format conversion model can be a neural network model. The training method of the format conversion model is existing technology and will not be described in detail here.

[0095] For example, when the initial format within the cluster is doc and the target format is doc, there is no need to call a format conversion model; when the initial format within the cluster is xls table format and the target format is doc, the format conversion model can be a table conversion model, which is used to adjust the text content of table format to doc format text content; when the initial format within the cluster is pdf file format and the target format is doc, the format conversion model can be a pdf conversion model, which is used to adjust the text content of pdf format to doc format text content; when the initial format within the cluster is jpg file format and the target format is doc, the format conversion model can be an image conversion model, which is used to adjust the text content of image format to doc format text content.

[0096] S144, the format conversion model is invoked to adjust the initial format corresponding to the content of each target text item in the format cluster to the target format, thereby obtaining the target regulatory text.

[0097] In one embodiment, the format conversion model is invoked to adjust the initial format of each target text item content within the format cluster to the target format. Then, the format-adjusted text item content is combined according to the combination order of the target text items to obtain the target regulatory text.

[0098] S15, parse the target regulatory text to obtain the content of the information items to be entered.

[0099] In at least one embodiment of this application, the information item to be entered refers to the information item content contained in the target regulatory text for entry into a preset system. The information item to be entered may be key information such as the regulatory body and the regulated body.

[0100] Combination Figure 4 This application describes the process for determining the content of the information item to be entered, as provided in the embodiments of this application. Optionally, parsing the target regulatory text to obtain the content of the information item to be entered includes:

[0101] S151, Obtain preset information item keywords and determine the target position of the preset information item keywords in the target regulatory text.

[0102] In one embodiment, the target regulatory text contains several preset information item keywords, which are used to uniquely identify the content of the information item to be entered. By obtaining the preset information item keywords, their target positions within the target regulatory text can be determined.

[0103] S152, Obtain the preset data format between the preset information item keywords and the information item content in the target regulatory text.

[0104] In one embodiment, the preset information item keywords and the information item content are combined according to a preset data format. This preset data format is pre-set; for example, it could be {preset information item keywords: information item content}. By obtaining the target position of the preset information item keywords in the target regulatory text and the preset data format between the preset information item keywords and the information item content, the corresponding information item content to be entered can be obtained.

[0105] S153, Select the content at the target location as the information item to be entered according to the preset data format.

[0106] S16, determine the regulatory type corresponding to the target regulatory text and the information entry preference corresponding to the regulatory type.

[0107] In at least one embodiment of this application, the regulatory type refers to the type of assistance issued by the regulatory agency to perform regulatory tasks. For example, the regulatory type may be assistance in performing investigations, freezing and deductions, supervision of labor arbitration, supervision of system complaints, etc.

[0108] Optionally, determining the regulatory type corresponding to the target regulatory text includes:

[0109] S161, Determine the pre-trained regulatory type to determine the model.

[0110] In one embodiment, the regulatory type determination model is a pre-trained model used to determine the corresponding regulatory type based on the target regulatory text. The input vector of the regulatory type determination model is historical regulatory text, and the output vector is the regulatory type. The historical regulatory text and corresponding regulatory types can be obtained through manual annotation, which is not limited here. The regulatory type determination model can be a neural network model. The training process of the model is existing technology and is not limited here.

[0111] S162, the regulatory type determination model is called to process the target regulatory text to obtain the regulatory type corresponding to the target regulatory text.

[0112] In at least one embodiment of this application, the information entry preference refers to the information entry requirements corresponding to different regulatory types. The information entry preference may include the component type preference and component position preference of each information item to be entered in the target panel within the preset system. In one embodiment, the component type may include text box type, drop-down box type, etc.; the component position preference refers to the position information of the content of the information item to be entered on the target panel.

[0113] Optionally, determining information entry preferences based on the regulatory type includes:

[0114] S163, determine the mapping relationship between the pre-set regulatory type and information entry preference.

[0115] S164, Traverse the mapping relationship to obtain the information entry preference corresponding to the regulatory type.

[0116] For example, taking a regulatory system complaint as the regulatory type, the information items to be entered include four items: regulatory unit, regulated department, inspection summary, and regulatory date selection. The component type preference for the regulatory unit, regulated department, and inspection summary is text box, while the component type preference for the regulatory date selection is dropdown. These are arranged sequentially on the target panel of the preset system according to the order of regulatory date, regulatory unit, regulated department, and inspection summary.

[0117] S17, The content of the information item to be entered is entered into the preset system according to the information entry preference.

[0118] In at least one embodiment of this application, the preset system refers to a pre-set system for storing regulatory text. Considering the reliability and privacy of data storage, the preset system can be a target node in a blockchain. In one embodiment, a script can be run via RPA (Robotic Process Automation) to input the content of the information items to be entered into the preset system according to the information input preferences.

[0119] Optionally, the step of entering the content of the information item to be entered into the preset system according to the information entry preference includes:

[0120] S171, determine the component type and component position corresponding to the information item to be entered based on the information entry preference.

[0121] In one embodiment, the component type may include a text box type, a drop-down box type, etc.

[0122] S172, construct the target component at the component location in the preset system according to the component type.

[0123] S173, The content of the information item to be entered is entered into the target component.

[0124] The information entry method based on artificial intelligence provided in this application improves information entry efficiency by parsing the target regulatory text to obtain the content of the information items to be entered and determining the information entry preferences corresponding to the target regulatory text. The information items to be entered into a preset system according to the information entry preferences. Furthermore, this application determines the combination order of target text items based on their importance, in descending order of importance, to obtain the initial regulatory text. When determining the information items to be entered, it prioritizes traversing regulatory texts with high importance, quickly finding the information items to be entered and avoiding the long query time caused by traversing the entire initial regulatory text, further improving information entry efficiency. This application can be applied to various functional modules of smart cities, such as smart government affairs and smart transportation, including the information entry module of smart cities, promoting the rapid development of smart cities.

[0125] Please see Figure 5 , Figure 5 This is a structural diagram of an artificial intelligence-based information input device provided in an embodiment of this application.

[0126] In some embodiments, the AI-based information input device 20 may include multiple functional modules composed of computer program segments. The computer programs for each program segment in the AI-based information input device 20 may be stored in the memory of a computer device and executed by at least one processor to perform (see details). Figure 1 (Description) Information entry function.

[0127] In this embodiment, the AI-based information input device 20 can be divided into multiple functional modules according to its functions. These functional modules may include: a request parsing module 201, a sequence determination module 202, a sequence combination module 203, a text adjustment module 204, a text parsing module 205, a type determination module 206, and an information input module 207. The term "module" in this application refers to a series of computer program segments that can be executed by at least one processor and perform a fixed function, stored in memory. In this embodiment, the functions of each module will be detailed in subsequent embodiments.

[0128] The request parsing module 201 can be used to parse the regulatory request when a regulatory request is received, and obtain the content of multiple target text items.

[0129] The order determination module 202 can be used to determine the importance of each of the target text items and determine the combination order of the target text items according to the order of decreasing importance.

[0130] The sequence combination module 203 can be used to combine the contents of the target text item according to the combination order to obtain the initial regulatory text.

[0131] The text adjustment module 204 can be used to determine the target format of the initial regulatory text and adjust the initial regulatory text according to the target format to obtain the target regulatory text.

[0132] The text parsing module 205 can be used to parse the target regulatory text to obtain the content of the information item to be entered.

[0133] The type determination module 206 can be used to determine the regulatory type corresponding to the target regulatory text and the information entry preference corresponding to the regulatory type.

[0134] The information entry module 207 can be used to enter the content of the information item to be entered into the preset system according to the information entry preference.

[0135] In at least one embodiment of this application, the sequence determination module 202 can also be used to obtain a target text item corresponding to each target text item content; obtain multiple historical text item contents corresponding to each target text item to form a historical text item content set; determine a preset historical input information item identifier corresponding to each historical text item content in the historical text item content set, and calculate the number of preset historical input information item identifiers to obtain the input quantity corresponding to each historical text item content; calculate the target input quantity corresponding to each target text item based on several input quantities; and determine the importance of each target text item content based on the target input quantity.

[0136] In at least one embodiment of this application, the text adjustment module 204 can also be used to determine the initial format corresponding to the content of each target text item to obtain an initial format set; cluster the multiple initial formats in the initial format set to obtain several format clusters; determine the pre-trained format conversion model corresponding to each format cluster; and call the format conversion model to adjust the initial format corresponding to the content of each target text item in the format cluster to the target format to obtain the target regulatory text.

[0137] In at least one embodiment of this application, the text parsing module 205 can be used to obtain preset information item keywords and determine the target position of the preset information item keywords in the target regulatory text; obtain a preset data format between the preset information item keywords and the information item content in the target regulatory text; and select the content at the target position as the information item content to be entered according to the preset data format.

[0138] In at least one embodiment of this application, the type determination module 206 can also be used to determine a pre-trained regulatory type determination model; call the regulatory type determination model to process the target regulatory text, and obtain the regulatory type corresponding to the target regulatory text.

[0139] In at least one embodiment of this application, the type determination module 206 can also be used to determine a pre-set mapping relationship between regulatory types and information entry preferences; and traverse the mapping relationship to obtain the information entry preferences corresponding to the regulatory type.

[0140] In at least one embodiment of this application, the information entry module 207 can also be used to determine the component type and component position corresponding to the information item to be entered according to the information entry preference; construct a target component at the component position in the preset system according to the component type; and enter the content of the information item to be entered into the target component.

[0141] See Figure 6 The diagram shown is a structural schematic of a computer device provided in an embodiment of this application. In a preferred embodiment of this application, the computer device 3 includes a memory 31, at least one processor 32, at least one communication bus 33, and a transceiver 34.

[0142] Those skilled in the art should understand that Figure 6 The structure of the computer device shown does not constitute a limitation of the embodiments of this application. It can be a bus structure or a star structure. The computer device 3 may also include more or fewer other hardware or software than shown, or different component arrangements.

[0143] In some embodiments, the computer device 3 is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices. The computer device 3 may also include client devices, which include, but are not limited to, any electronic product that can interact with a client via a keyboard, mouse, remote control, touchpad, or voice control device, such as personal computers, tablet computers, smartphones, and digital cameras.

[0144] It should be noted that the computer device 3 described is merely an example. Other existing or future electronic products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0145] In some embodiments, the memory 31 stores a computer program that, when executed by the at least one processor 32, implements all or part of the steps in the artificial intelligence-based information entry method described above. The memory 31 includes a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0146] Furthermore, the computer-readable storage medium may primarily include a program storage area and a data storage area, wherein the program storage area may store the operating system, at least one application required for a function, etc.; and the data storage area may store data created based on the use of blockchain nodes, etc.

[0147] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0148] In some embodiments, the at least one processor 32 is the control unit of the computer device 3, connecting various components of the computer device 3 via various interfaces and lines. It executes programs or modules stored in the memory 31 and calls data stored in the memory 31 to perform various functions and process data. For example, when the at least one processor 32 executes a computer program stored in the memory, it implements all or part of the steps of the artificial intelligence-based information entry method described in this application embodiment; or it implements all or part of the functions of the information entry device. The at least one processor 32 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips.

[0149] In some embodiments, the at least one communication bus 33 is configured to enable communication between the memory 31 and the at least one processor 32, etc.

[0150] Although not shown, the computer device 3 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 32 via a power management device, thereby enabling functions such as charging, discharging, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The computer device 3 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0151] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, a computer device, or a network device, etc.) or a processor to execute portions of the methods described in the various embodiments of this application.

[0152] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0153] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0154] Furthermore, the functional modules in the various embodiments of this application 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. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0155] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that it can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other elements or, and the singular does not exclude the plural. Multiple elements or devices recited in the specification may also be implemented by a single element or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. An information entry method based on artificial intelligence, characterized in that, The information entry method based on artificial intelligence includes: When a regulatory request is received, the regulatory request is parsed to obtain the content of multiple target text items; Determine the importance of each of the target text items, and determine the combination order of the target text items according to the order of decreasing importance; The target text items are combined according to the given combination order to obtain the initial regulatory text; Determine the target format of the initial regulatory text, and adjust the initial regulatory text according to the target format to obtain the target regulatory text; The target regulatory text is parsed to obtain the content of the information items to be entered; Determining the regulatory type corresponding to the target regulatory text and the information entry preference corresponding to the regulatory type includes: determining a pre-set mapping relationship between regulatory types and information entry preferences; traversing the mapping relationship to obtain the information entry preference corresponding to the regulatory type; The process of entering the information item to be entered into a preset system according to the information entry preference includes: determining the component type and component position corresponding to the information item to be entered according to the information entry preference; constructing a target component at the component position in the preset system according to the component type; and entering the information item to be entered into the target component.

2. The information entry method based on artificial intelligence according to claim 1, characterized in that, Determining the importance of the content of each target text item includes: Obtain the target text item corresponding to the content of each target text item; Obtain the contents of multiple historical text items corresponding to each target text item, and form a historical text item content set; Determine the preset historical input information item identifier corresponding to each historical text item content in the historical text item content set, and calculate the number of preset historical input information item identifiers to obtain the input quantity corresponding to each historical text item content. Calculate the target input quantity corresponding to each target text item based on several input quantities; The importance of each target text item is determined based on the target number of entries.

3. The information entry method based on artificial intelligence according to claim 1, characterized in that, The step of adjusting the initial regulatory text according to the target format to obtain the target regulatory text includes: Determine the initial format corresponding to the content of each target text item to obtain an initial format set; Multiple initial formats within the initial format set are clustered to obtain several format clusters. Determine the pre-trained format conversion model corresponding to each of the aforementioned format clusters; The format conversion model is invoked to adjust the initial format of each target text item within the format cluster to the target format, thereby obtaining the target regulatory text.

4. The information entry method based on artificial intelligence according to claim 1, characterized in that, The process of parsing the target regulatory text yields the content of the information items to be entered, including: Obtain keywords for preset information items and determine the target location of the keywords for preset information items in the target regulatory text; Obtain the preset data format between the preset information item keywords and the information item content in the target regulatory text; The content at the target location is selected as the information item to be entered according to the preset data format.

5. The information entry method based on artificial intelligence according to claim 1, characterized in that, Determining the regulatory type corresponding to the target regulatory text includes: Determine the type of pre-trained supervision to determine the model; The regulatory type determination model is invoked to process the target regulatory text, thereby obtaining the regulatory type corresponding to the target regulatory text.

6. An information input device based on artificial intelligence, characterized in that, The artificial intelligence-based information input device includes: The request parsing module is used to parse the regulatory request when it is received, and obtain the content of multiple target text items; The sequence determination module is used to determine the importance of each of the target text items and to determine the combination order of the target text items according to the order of decreasing importance. The sequential combination module is used to combine the contents of the target text item according to the combination order to obtain the initial regulatory text. The text adjustment module is used to determine the target format of the initial regulatory text and adjust the initial regulatory text according to the target format to obtain the target regulatory text; The text parsing module is used to parse the target regulatory text to obtain the content of the information items to be entered; The type determination module is used to determine the regulatory type corresponding to the target regulatory text and the information entry preference corresponding to the regulatory type, including: determining a pre-set mapping relationship between regulatory types and information entry preferences; traversing the mapping relationship to obtain the information entry preference corresponding to the regulatory type; An information entry module is used to enter the content of the information item to be entered into a preset system according to the information entry preference, including: determining the component type and component position corresponding to the information item to be entered according to the information entry preference; constructing a target component at the component position in the preset system according to the component type; and entering the content of the information item to be entered into the target component.

7. A computer device, characterized in that, The computer device includes a processor, which executes a computer program stored in a memory to implement the artificial intelligence-based information entry method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by the processor, it implements the information entry method based on artificial intelligence as described in any one of claims 1 to 5.

Images