Form filling method and device

Abstract

The invention discloses a form filling method and device, and relates to the technical field of computers. A specific embodiment of the form filling method comprises the steps of determining target scene information corresponding to a to-be-filled form in response to a received form filling request; acquiring a corresponding target feature parameter according to the target scene information; and inputting the target feature parameters into a target algorithm model to obtain a recommendation result, and filling the to-be-filled form according to the recommendation result. The implementation mode can be suitable for various business scenes, the form filling efficiency is improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a form filling method and device. Background Art

[0002] In actual business systems, forms are usually used to circulate business data. For example, users fill in business data in the form displayed on the front-end page. After the user submits the form, the business system sends the form carrying the business data from the front-end to the back-end to perform logical operations, data storage and other processing steps. It can be seen that forms that realize the flow of business data are an important way of data interaction. At present, as business logic becomes increasingly complex, form items gradually increase, and form content involves many aspects, currently manual selection or manual filling is mainly used to complete form filling, or auxiliary plug-ins and other automated methods are used to fill in forms.

[0003] In the process of implementing the present invention, the inventors found that the prior art has at least the following problems:

[0004] Using auxiliary plug-ins to fill in forms can only be used in specific business scenarios and is difficult to apply to different scenarios; using manual filling consumes a lot of manpower costs and has low form filling efficiency. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a form filling method and device, which can be applied to a variety of scenarios, improve form filling efficiency, and reduce labor costs.

[0006] To achieve the above object, according to a first aspect of an embodiment of the present invention, a form filling method is provided, comprising:

[0007] In response to receiving the form filling request, determining target scene information corresponding to the form to be filled;

[0008] Acquire corresponding target feature parameters according to the target scene information;

[0009] The target feature parameters are input into a target algorithm model to obtain a recommendation result, and the form to be filled is filled according to the recommendation result.

[0010] Optionally, before acquiring corresponding target feature parameters according to the target scene information, the method further includes:

[0011] Traversing a preset scene information set, acquiring scene information included in the scene information set, and determining feature arrangement information corresponding to the scene information;

[0012] Acquire the business data corresponding to the scene information according to the feature arrangement information;

[0013] Convert the service data according to the feature arrangement information to obtain feature parameters corresponding to the scene information;

[0014] The scene information is associated with the corresponding characteristic parameters and stored.

[0015] Optionally, converting the service data according to the feature arrangement information includes:

[0016] Parsing the feature arrangement information to obtain corresponding field mapping relationships and field dependency relationships;

[0017] The business data is converted according to the field mapping relationship and the field dependency relationship.

[0018] Optionally, acquiring business data corresponding to the scenario information according to the feature arrangement information includes:

[0019] Parsing the feature arrangement information to obtain a corresponding remote call interface;

[0020] The remote call interface is used to asynchronously obtain the business data corresponding to the scenario information from a preset business data set.

[0021] Optionally, before using the remote call interface to asynchronously acquire the business data corresponding to the scenario information from a preset business data set, the method further includes:

[0022] Use message middleware to asynchronously receive business data of multiple business domains, extract and encapsulate the business data of the multiple business domains, and store the business data that has undergone data extraction and data encapsulation into a business data set.

[0023] Optionally, before inputting the target feature parameters into the target algorithm model, the method further includes:

[0024] Acquire a corresponding model identifier according to the target scene information;

[0025] The target algorithm model is determined from a preset algorithm model set according to the model identifier.

[0026] Optionally, after filling the to-be-filled form according to the recommendation result, the method further includes:

[0027] In response to receiving the form modification request, modifying the recommended results included in the form to be filled in to obtain an actual filling result;

[0028] The target algorithm model is evaluated and optimized according to the recommendation result and the actual filling result.

[0029] According to a second aspect of an embodiment of the present invention, a form filling device is provided, comprising:

[0030] A determination module, configured to determine target scene information corresponding to the form to be filled in response to receiving a form filling request;

[0031] An acquisition module, used to acquire corresponding target feature parameters according to the target scene information;

[0032] The filling module is used to input the target feature parameters into the target algorithm model to obtain a recommendation result, and fill the form to be filled according to the recommendation result.

[0033] Optionally, the device further comprises:

[0034] A traversal module, used to traverse a preset scene information set, obtain scene information included in the scene information set, and determine feature arrangement information corresponding to the scene information;

[0035] An acquisition module, used for acquiring business data corresponding to the scene information according to the feature arrangement information;

[0036] A conversion module, used to convert the business data according to the feature arrangement information to obtain feature parameters corresponding to the scene information;

[0037] The storage module is used to store the scene information in association with the corresponding feature parameters.

[0038] Optionally, converting the service data according to the feature arrangement information includes:

[0039] Parsing the feature arrangement information to obtain corresponding field mapping relationships and field dependency relationships;

[0040] The business data is converted according to the field mapping relationship and the field dependency relationship.

[0041] Optionally, acquiring business data corresponding to the scenario information according to the feature arrangement information includes:

[0042] Parsing the feature arrangement information to obtain a corresponding remote call interface;

[0043] The remote call interface is used to asynchronously obtain the business data corresponding to the scenario information from a preset business data set.

[0044] Optionally, the device further comprises:

[0045] The encapsulation module is used to asynchronously receive business data of multiple business domains using the message middleware, extract and encapsulate the business data of the multiple business domains, and store the business data after data extraction and data encapsulation into the business data set.

[0046] Optionally, the device further comprises:

[0047] An identification module, used to obtain a corresponding model identifier according to the target scene information;

[0048] The determination module is used to determine the target algorithm model from a preset algorithm model set according to the model identifier.

[0049] Optionally, the device further comprises:

[0050] A modification module, configured to modify the recommended results included in the form to be filled in response to receiving a form modification request, to obtain an actual filling result;

[0051] An optimization module is used to evaluate and optimize the target algorithm model according to the recommendation result and the actual filling result.

[0052] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, including:

[0053] one or more processors;

[0054] a storage device for storing one or more programs,

[0055] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any one of the above embodiments.

[0056] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method described in any one of the above embodiments is implemented.

[0057] An embodiment of the above invention has the following advantages or beneficial effects: determining the scenario information corresponding to the form to be filled, obtaining the corresponding feature parameters according to the scenario information, and generating the recommended results of the form to be filled according to the feature parameters, which can be applicable to the form filling process in various business scenarios, improve the efficiency of form filling, and reduce labor costs; pre-setting feature arrangement information corresponding to the scenario information, converting business data into feature parameters according to the feature arrangement information, which can improve the correlation between feature parameters and scenario information, and the feature arrangement information includes business data mapping relationships of various business scenarios, which can associate business data of various business scenarios and improve the flexibility of form filling; converting business data according to field mapping relationships and field dependency relationships can improve the conversion efficiency and accuracy of business data, maintain the dependencies and associations between business data, The use of remote call interface to asynchronously obtain business data can improve the efficiency of obtaining business data and avoid blocking the filling process of other forms; data extraction and data encapsulation of business data can improve the conversion efficiency and accuracy of business data, ensure that business data conforms to the conversion rules, and thus improve the efficiency and accuracy of form filling; determine the corresponding model identifier according to the scenario information of the form to be filled, and determine the target algorithm model corresponding to the form to be filled according to the model identifier, so as to use the corresponding algorithm model according to different business scenarios, and improve the accuracy, flexibility and scalability of form filling; modify the recommended results to obtain the actual filling results, which can improve the flexibility and accuracy of form filling; optimize the target algorithm model according to the recommended results and the actual filling results, which can improve the accuracy of the target algorithm model and reduce R&D costs and maintenance costs.

[0058] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0060] Figure 1 is a schematic diagram of the main process of the form filling method according to an embodiment of the present invention;

[0061] Figure 2 is a schematic diagram of the overall process of a method for filling in a form according to a reference embodiment of the present invention;

[0062] Figure 3 is a schematic diagram of associated storage of characteristic parameters of a form filling method according to a reference embodiment of the present invention;

[0063] Figure 4 is a schematic diagram of feature arrangement information of a method for filling in a form according to a reference embodiment of the present invention;

[0064] Figure 5 is a schematic diagram of the main process of a form filling method according to a reference embodiment of the present invention;

[0065] Figure 6 is a schematic diagram of the main process of a form filling method according to another reference embodiment of the present invention;

[0066] Figure 7 is a schematic diagram of the main process of a form filling method according to yet another reference embodiment of the present invention;

[0067] Figure 8 is a schematic diagram of main modules of a form filling device according to an embodiment of the present invention;

[0068] Fig. 9 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0069] Fig.10 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0071] It should be noted that in the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0072] In actual business systems, forms are usually used to circulate business data. For example, users fill in business data in the form displayed on the front-end page. After the user submits the form, the business system sends the form carrying the business data from the front-end to the back-end to perform logical operations, data storage and other processing steps. It can be seen that forms that realize the flow of business data are an important way of data interaction. At present, as business logic becomes increasingly complex, form items gradually increase, and form content involves many aspects, the current main method of completing form filling is manual selection or manual filling, or using auxiliary plug-ins and other automated methods to fill in the form. The automated filling method is mainly based on fixed matching rules and filtering rules to realize automatic form filling. Different matching rules or filtering rules need to be formulated in different business scenarios.

[0073] Using auxiliary plug-ins to fill in forms can only be used in specific business scenarios and is difficult to apply to different scenarios. It is necessary to develop corresponding automatic filling methods for different scenarios, resulting in high R&D and maintenance costs; using manual filling consumes a lot of manpower costs, and the form filling efficiency and accuracy are low.

[0074] In view of this, according to a first aspect of an embodiment of the present invention, a form filling method is provided.

[0075] Figure 1 Schematic diagram of the main process of the form filling method according to an embodiment of the present invention. Figure 1 As shown, the form filling method according to the embodiment of the present invention mainly includes the following steps S101 to S103.

[0076] Step S101, in response to receiving a form filling request, determining target scene information corresponding to the form to be filled.

[0077] A form filling request is a request for automatically filling a form to be filled. A form filling request can be initiated in any business scenario where data needs to be transferred through a form. For example, in a business scenario where goods are put on the shelves, form information such as the name of the goods, the price of the goods, and the type of goods need to be filled in, or in a business scenario where the goods code, the quantity of the goods, the mode of transportation, and other form information of the goods out of the warehouse need to be filled in. A form filling request can be initiated in the above business scenarios. After receiving the form filling request, the execution subject of the embodiment of the present invention parses the form filling request and obtains the target scenario information corresponding to the form to be filled. Scenario information refers to the relevant information of the business scenario to which the form to be filled belongs. In addition to the goods on the shelves and logistics transportation mentioned above, business scenarios also include: pre-sales consultation scenarios, commodity ordering scenarios, after-sales service scenarios, and the like. Different business scenarios correspond to different scenario information. When a business scenario includes multiple forms to be filled, each form to be filled corresponds to different scenario information. The scenario information includes: business scenario code, business scenario name, business scenario description, form code to be filled, form name to be filled, fields to be filled, form description to be filled, and the like.

[0078] Figure 2 FIG. 1 is a schematic diagram of the overall process of a method for filling in a form according to a reference embodiment of the present invention. Figure 2 As shown, after receiving the form filling request, the execution subject of the embodiment of the present invention parses the form filling request to obtain the target scene information corresponding to the form to be filled, and determines the to-be-filled fields corresponding to the form to be filled according to the target scene information.

[0079] As another example, after receiving the form filling request, the form filling request is parsed to obtain the target scene information corresponding to the form to be filled as follows: "{'sceneId':'s001'; 'sceneName':'customerService'; 'formId':'f002'; 'formName':'serviceRecord'}", wherein "'sceneId':'s001'" indicates that the business scene number is "s001", "'sceneName':'customerService'" indicates that the business scene name is "user service scene", "'formId':'f002'" indicates that the form code to be filled is "f002", and "'formName':'serviceRecord'" indicates that the name of the form to be filled is "service process record".

[0080] Parsing the form filling request and obtaining the target scenario information can improve the recognition of the form to be filled, quickly determine the business scenario and form information corresponding to the form to be filled, and provide the prerequisite for accurately filling in the form content.

[0081] Step S102: acquiring corresponding target feature parameters according to the target scene information.

[0082] After obtaining the target scene information, the target feature parameters corresponding to the target scene information are obtained. The target feature parameters are feature parameters used to input the target algorithm model and obtain the recommendation results. The target feature parameters are obtained after parsing and mapping the business data. For example, before obtaining the target feature parameters, a pre-set screening template is obtained to screen the business data of multiple business scenes, select the business data associated with any scene information, convert the business data into feature parameters according to the mapping template or obtain the feature parameters corresponding to the business data according to the association template, and encapsulate the feature parameters corresponding to the same scene information according to the encapsulation template for easy acquisition. The content of the target feature parameter can be a string, a number, a Boolean value, etc., and the data structure for storing the target feature parameter can be an array, a linked list, a matrix, a mapping table, etc. The encapsulated feature parameters and the corresponding scene information are stored in a relational database or a non-relational database (for example, Redis). After determining the target scene information, the target feature parameters associated with the target scene information are searched in the relational database or the non-relational database.

[0083] Figure 3 FIG. 1 is a schematic diagram of the associated storage of characteristic parameters of a form filling method according to a reference embodiment of the present invention. Figure 3 As shown, the steps of associating and storing feature parameters include: obtaining corresponding feature arrangement information according to scenario information, parsing corresponding field mapping relationships according to the feature arrangement information, obtaining a remote call interface included in the feature arrangement information, asynchronously obtaining business data using the remote call interface, performing field mapping on the business data according to the field mapping relationship to obtain feature parameters, performing data encapsulation on the feature parameters according to the encapsulation rules included in the feature arrangement information, and associating and storing the encapsulated feature parameters with the scenario information.

[0084] For another example, the business data obtained in business scenario A includes order price, order type, quantity of goods included in the order, and coupons used in the order; the data associated with the form including order price and order type are obtained according to the screening template; the order price and order type are mapped to "orderPrice-orderType" according to the mapping template, that is, the specific order price and order type are removed, and only the name of the business data is retained; the mapping result is encapsulated using an array, and the business scenario A is used as the key value and the mapping result is used as the value associated with the key value, and stored in the cache Redis. After obtaining the target scenario information of business scenario A, the corresponding mapping result is obtained in Redis according to the target scenario information.

[0085] Acquiring corresponding target feature parameters according to target scene information can improve the flexibility of the target feature parameters, decouple the target scene information from the corresponding target feature parameters, and improve the acquisition efficiency of the target feature parameters.

[0086] According to a reference embodiment of the present invention, before obtaining the corresponding target feature parameters according to the target scene information, the method also includes: traversing a preset scene information set, obtaining the scene information included in the scene information set, and determining feature arrangement information corresponding to the scene information; obtaining business data corresponding to the scene information according to the feature arrangement information; converting the business data according to the feature arrangement information to obtain the feature parameters corresponding to the scene information; and storing the scene information in association with the corresponding feature parameters.

[0087] Before obtaining the target feature parameters, the pre-set scene information set is traversed, and the scene information set is a collection of scene information; each scene information corresponds to a feature arrangement information, and the feature arrangement information includes business data under multiple business scenarios. The business data under different business scenarios are associated through business scenario numbers, and the feature arrangement information is a combination of business data of multiple business scenarios; the feature arrangement information is pre-configured, modifiable, and addable and deleteable. Specifically, the feature arrangement information corresponding to different scene information is pre-written in the configuration file, and the corresponding business data is obtained from the business data set according to the business data included in the feature arrangement information; the feature arrangement information also includes the conversion rules between business data and feature parameters, and the conversion rules include: when the business data is a decimal, modify the valid digits of the business data; convert multiple business data into a matrix form, an array form or a string type; obtain the corresponding business data range according to multiple business data, etc., and convert the business data into feature parameters according to the conversion rules. After obtaining the feature parameters, the scene information is associated with the corresponding feature parameters and stored, so that the corresponding feature parameters can be obtained according to the scene information.

[0088] For example, Figure 2 As shown, after determining the to-be-filled fields corresponding to the to-be-filled form, the step of acquiring characteristic parameters is executed, wherein the step of "acquiring characteristic parameters" is pointed to by the dotted arrow to the "asynchronous acquisition module of characteristic parameters", which means that before executing the step of "acquiring characteristic parameters", it is necessary to first execute the steps shown in the "asynchronous acquisition module of characteristic parameters", specifically, in the "asynchronous acquisition module of characteristic parameters", the characteristic arrangement information is first acquired, and then the business data is asynchronously collected, and then the business data is converted according to the characteristic arrangement information to obtain characteristic parameters, and the characteristic parameters are encapsulated and stored in association with the scene information. Therefore, when executing the step of acquiring characteristic parameters, the target characteristic parameters associated with the target scene information are determined from the stored characteristic parameters. In the "Feature Parameter Asynchronous Collection Module", the step of "Feature Orchestration Information Acquisition" is pointed to the "Feature Information Orchestration Module" by a dotted arrow, which means that before executing the "Feature Orchestration Information Acquisition" step, it is necessary to first execute the steps shown in the "Feature Information Orchestration Module". Specifically, in the "Feature Information Orchestration Module", the feature information is first edited, then mapped, and then encapsulated. The feature information includes the business data name, the dependency relationship between business data, the remote calling method, the field mapping relationship of the business data, and so on.

[0089] As another example, the scene information obtained from the scene information set includes: business scene number "scene002", business scene name "after-sales maintenance business scene", and feature arrangement information corresponding to the scene information is obtained, the feature arrangement information includes business data names of two business scenes, namely, after-sales maintenance business scene and order business scene, specifically including: maintenance time, maintenance location, maintenance personnel number, maintenance result, maintenance product type, product price, order time; according to the above business data names, the corresponding business data is obtained, and the business data is converted into a mapping table form according to the conversion rules included in the feature arrangement information, and the maintenance time and order time are converted into "yyyy-MM-dd" format, where "yyyy" represents year, "MM" represents month, and "dd" represents date, the maintenance location is converted into longitude and latitude information, and the maintenance personnel number is deleted; the feature parameters obtained according to the above conversion rules are "{'repairTime':'y1-M1-d1';'l ocation':'39.9-116.3';'type':'electrical';'result':'success';'price':'100';'orderTime':'y2-M2-d2'}", where "'repairTime':'y1-M1-d1'" represents the repair time, "'location':'39.9-116.3'" represents the longitude and latitude information of the repair location (i.e., longitude-latitude), "type':'electrical'" represents the type of repaired product is electrical appliances, "result':'success'" represents the repair result is successful, "'price':'100'" represents the product price, and "'orderTime':'y2-M2-d2'" represents the order time; the above feature parameters are associated with the scene information with the business scene number "scene002" and stored.

[0090] Pre-setting feature arrangement information corresponding to the scenario information and converting business data into feature parameters according to the feature arrangement information can improve the correlation between feature parameters and scenario information. The feature arrangement information includes business data mapping relationships of multiple business scenarios, which can associate business data of multiple business scenarios and improve the flexibility of form filling.

[0091] According to another reference embodiment of the present invention, the business data is converted according to the feature arrangement information, including: parsing the feature arrangement information to obtain corresponding field mapping relationships and field dependencies; converting the business data according to the field mapping relationships and field dependencies.

[0092] Parse the feature arrangement information to obtain the field mapping relationship and field dependency relationship included in the feature arrangement information. The field mapping relationship represents the rules for field mapping of business data. Different field mapping rules are used for business data of different data types and different data structures. For example, the left end of binary data that does not meet the length requirement is padded with zeros to make the binary data meet the length requirement; special characters are removed or converted for string type data containing special characters to make the string type data contain no special characters; new business data is generated based on the association relationship between business data, thereby strengthening the association relationship between business data. The field mapping relationship is configurable, and the field mapping relationship is pre-set according to the actual needs of business data conversion.

[0093] Field dependency represents an association relationship between business data. For example, the first business data may include multiple data fields. When the data field indicates the second business data, there is a dependency relationship between the first business data and the second business data. The acquisition or generation of the first business data depends on the acquisition or generation of the second business data. Therefore, for two business data with a dependency relationship, the conversion order indicated by the dependency relationship must be followed during data conversion. The business data that does not depend on other business data must be converted first, and then the business data that has a dependency relationship with the business data must be converted.

[0094] Figure 4 FIG. 1 is a schematic diagram of feature arrangement information of a method for filling in a form according to a reference embodiment of the present invention. Figure 4 As shown, based on the business data included in multiple business scenarios, multiple feature orchestration information are pre-set, wherein each business scenario includes a business data primary key and multiple business data. Specifically, the business data primary key is a unique business scenario number; each feature orchestration information includes a scenario information, a remote call interface and business data under multiple business scenarios, and the business data under different business scenarios are associated through the business data primary key. After determining the feature orchestration information based on the scenario information, the field dependency is determined based on the business data included in the feature orchestration information, and field mapping is performed.

[0095] As another example, the field mapping relationship obtained by parsing the feature arrangement information is "{'orderPrice', 'orderType':'orderPrice-orderType'; 'orderLocation':'city', 'district', 'country'; 'orderTime':'year', 'month', 'day'}", where "'orderPrice', 'orderType':'orderPrice-orderType'" means that the order price and order type are combined into a new business data "order price-order type", and "'orderLocation':'city', 'district', 'country'" means that the order address is split into three business data of "province", "city" and "county". Data, "'orderTime':'year', 'month', 'day'" means splitting the order time into three business data of "year", "month" and "day"; parsing the feature arrangement information to obtain the field dependency relationship is "{'dataB1':'dataB2'; 'dataB2':'dataB3'}", where "'dataB1':'dataB2'" means that the data field of business data B1 includes business data B2, that is, business data B1 depends on business data B2, and "'dataB2':'dataB3'" means that the data field of business data B2 includes business data B3, that is, business data B2 depends on business data B3. Therefore, data conversion is performed on business data B3 first, and then data conversion is performed on business data B2 that depends on business data B3, and then data conversion is performed on business data B1 that depends on business data B2.

[0096] Converting business data based on field mapping relationships and field dependencies can improve the conversion efficiency and accuracy of business data and maintain the dependencies and associations between business data.

[0097] According to another reference embodiment of the present invention, business data corresponding to the scenario information is obtained according to the feature arrangement information, including: parsing the feature arrangement information to obtain a corresponding remote call interface; and using the remote call interface to asynchronously obtain the business data corresponding to the scenario information from a pre-set business data set.

[0098] The feature arrangement information includes a remote call interface. The corresponding remote call interface is pre-set in the feature arrangement information. One feature arrangement information corresponds to one remote call interface. The remote call interface is used to obtain business data. The remote call interface includes: the protocol information followed by the interface, the network address and port information for storing business data indicated by the interface, the name of the interface method for obtaining business data, and interface parameters. The interface parameters include scenario information and acquisition conditions (for example, the number of business data to be obtained, whether duplicate data is allowed, whether business data needs to be encapsulated, etc.). The network address included in the remote call interface indicates a business data set for storing business data. The remote call interface is used to obtain business data corresponding to the scenario information from the business data set. Using the remote call interface to obtain business data is asynchronous, that is, it allows the creation of multiple threads, and different remote call interfaces are used in different threads to obtain business data in the business data set in parallel.

[0099] For example, Figure 2 As shown, in the "Feature Parameter Asynchronous Acquisition Module", the step of "Asynchronous Acquisition of Business Data" is pointed to the "Business Data Preparation Module" by a dotted arrow, which means that before executing the step of "Asynchronous Acquisition of Business Data", it is necessary to first execute the steps shown in the "Business Data Preparation Module". Specifically, in the "Business Data Preparation Module", business data is first obtained from various business scenarios, business data is extracted according to the extraction template, business data is encapsulated according to the encapsulation template, and the encapsulated business data is temporarily stored in the message queue or cache. As another example, Figure 4 As shown, each feature arrangement information includes a remote call interface, and the remote call interface is used to obtain the business data corresponding to the feature arrangement information from a preset business data set.

[0100] As another example, the remote call interface obtained by parsing the feature arrangement information is "https: / / www.c1c2c3.com:8080 / getData?sceneId=1234&duplicate=false&dataCount=10", wherein "https: / / " represents the protocol information followed by the interface, "www.c1c2c3.com:8080" represents the network address and port information for storing business data indicated by the interface, "getData" represents the name of the interface method for obtaining business data, and "sceneId=1234&duplicate=false&dataCount=10" represent interface parameters. Specifically, the scene information includes a business scene number of "1234", duplicate data is not allowed to be obtained, and the number of business data obtained is 10; the business data is obtained according to the above remote call interface.

[0101] Acquiring business data through remote calling asynchronous interfaces included in feature orchestration information can improve the efficiency of acquiring business data, ensure that the data acquisition process does not affect other business data processes such as data conversion, data encapsulation, and algorithm model processing, and efficiently utilize network resources.

[0102] According to another reference embodiment of the present invention, before using the remote call interface to asynchronously obtain the business data corresponding to the scenario information from a pre-set business data set, the method also includes: using a message middleware to asynchronously receive business data of multiple business domains, performing data extraction and data encapsulation on the business data of the multiple business domains, and storing the business data that has completed data extraction and data encapsulation in the business data set.

[0103] Before asynchronously obtaining business data from the business data set, use the message middleware to asynchronously receive business data from multiple business domains. Business domains represent business scenarios, business modules or business fields. Different business domains will generate different business data, and different business data will also flow between different business domains. After receiving business data from different business domains, extract the business data. According to the pre-set data extraction template, extract the business data related to form filling, and remove the business data not related to form filling; encapsulate the extracted business data, and select the corresponding data structure according to the pre-set data encapsulation rules to encapsulate the business data of multiple business domains, so that the encapsulated business data corresponds to the scenario information; store the encapsulated business data of multiple business domains in the business data set, so as to facilitate the subsequent acquisition of the corresponding business data according to the scenario information through the remote call interface. The message middleware used to receive business data includes: ActiveMQ, RabbitMQ, RocketMQ, Kafka and other message queues.

[0104] Exemplarily, a Kafka message queue is used to receive business data C1, business data C2, and business data C3 from business domain C, and business data D1, business data D2, and business data D3 from business domain D; according to a data extraction template of a pre-set scenario information E, business data C1, business data C2, business data D1, and business data D3 related to form filling are extracted, and business data C3 and business data D2 are removed; according to a data encapsulation rule of the pre-set scenario information E, an array is used to encapsulate the above-extracted business data to obtain "[business data C1, business data C2, business data D1, business data D3]", and then an array is used to encapsulate the business scenario number "0321" included in the scenario information E and the above-mentioned business data to obtain "[0321, [business data C1, business data C2, business data D1, business data D3]]"; the encapsulation result including the business scenario number and the extracted business data is stored in the business data set, so as to facilitate the subsequent acquisition of the business data corresponding to the scenario information through a remote call interface.

[0105] Data extraction and data encapsulation of business data can improve the conversion efficiency and accuracy of business data, ensure that business data complies with conversion rules, and thus improve the efficiency and accuracy of form filling.

[0106] Step S103: input the target feature parameters into a target algorithm model to obtain a recommendation result, and fill in the form to be filled in according to the recommendation result.

[0107] After obtaining the target feature parameters, the target feature parameters are input into the corresponding target algorithm model, so that the target algorithm model generates the corresponding recommendation results according to the target feature parameters. A plurality of algorithm models are pre-set, and the corresponding target algorithm model is determined according to the scenario information, data type, encapsulation format, business scenario involved and other information corresponding to the target feature parameters. The recommendation results generated by the target algorithm model include a plurality of data fields, and the to-be-filled form corresponding to the data field name is filled according to the data field names corresponding to the plurality of data fields. Specifically, in the recommendation results, a data field name corresponds to a plurality of data fields, each data field corresponds to a recommendation score, and the range of the recommendation score is, for example, between 0 and 1. The data field with the largest recommendation score is filled into the to-be-filled field corresponding to the to-be-filled form, and the remaining data fields are used as alternative fields for the to-be-filled fields; a manual review step is introduced, and the business personnel review the recommendation results. If the review fails, the business personnel select a more appropriate data field from the above alternative fields to fill the to-be-filled form. The algorithm models applicable to the embodiments of the present invention include: decision tree model, linear regression model, clustering model, annotation model, Bayesian model, hidden Markov model, universal language model, etc.

[0108] For example, Figure 2 As shown, after obtaining the characteristic parameters, the characteristic parameters are input into the algorithm model to obtain the corresponding recommendation results, and the form is filled with the recommendation results. As another example, the business scenario number corresponding to the obtained target characteristic parameters is "2345", the data type is a floating point type, the encapsulation format is a mapping table, and the business scenarios involved include business scenarios F1 and F2. The corresponding target algorithm model is obtained according to the above information; the target characteristic parameters are input into the target algorithm model, and the recommendation results obtained are "{'field1':'G1(0.9),G2(0.7),G3(0.5),G4(0.2)'; 'field2':'H1(0.95),H2(0.8),H3(0.6)'}", where "'field1':'G1(0.9),G2(0.7),G3(0.5) ,G4(0.2)'"The field "field1" to be filled has 4 recommended data fields (data field G1, data field G2, data field G3 and data field G4), and the field "field2" to be filled has 3 recommended data fields (data field H1, data field H2 and data field H3). The decimal in the brackets after each data field represents the recommended score. The data field with the largest recommended score corresponding to each field to be filled is filled into the form to be filled, that is, data field G1 is the recommended result of the field "field1" to be filled, data field H1 is the recommended result of the field "field2" to be filled, and the remaining data fields are used as alternative fields.

[0109] Determining the target algorithm model according to the target feature parameters and obtaining the recommendation results according to the target algorithm model can improve the efficiency and accuracy of form filling and increase the flexibility of form filling.

[0110] According to a reference embodiment of the present invention, before inputting the target feature parameters into the target algorithm model, the method further includes: obtaining a corresponding model identifier based on the target scene information; and determining the target algorithm model from a preset algorithm model set based on the model identifier.

[0111] An algorithm model set is pre-set, and the algorithm model set includes multiple algorithm models. A corresponding model identifier is set for each algorithm model. Different algorithm models have different model identifiers. The model identifier is used to indicate the algorithm model and is unique. The target scene information is parsed to obtain the model identifier included in the target scene information, and the corresponding target algorithm model is determined according to the model identifier. The model identifier can indicate an algorithm model or a group of algorithm models. When the model identifier indicates a group of algorithm models, the execution order of the algorithm models in the group is determined according to the arrangement order of the algorithm models in the group, and the target feature parameters are input into the first algorithm model indicated by the execution order. The execution result of the algorithm model is used as the input parameter of the next algorithm model, and the execution is performed in sequence according to the execution order. The execution result of the last algorithm model indicated by the execution order is used as the recommendation result.

[0112] Exemplarily, the pre-set algorithm model set includes four algorithm models, namely "{'model_J1':'decisionTree'; 'model_J2':'svm', 'model_J3':'cluster', 'model_J4':'gpt-3'}", among which, "'model_J1':'decisionTree'" indicates that the model identifier of the decision tree model is "model_J1", "'model_J2':'svm'" indicates that the model identifier of the support vector machine model is "model_J2", "'model_J3':'cluster'" indicates that the model identifier of the clustering model is "model_J3", and "'model_J4':'gpt-3'" indicates that the model identifier of the general language model is "model_J4"; the target scene information is parsed to obtain the corresponding algorithm identifier "model_J3", and therefore, the clustering model is used as the target algorithm model.

[0113] The corresponding model identifier is determined according to the scenario information of the form to be filled, and the target algorithm model corresponding to the form to be filled is determined according to the model identifier. The corresponding algorithm model can be used according to different business scenarios to improve the accuracy, flexibility and scalability of form filling.

[0114] According to another reference embodiment of the present invention, after filling the form to be filled according to the recommendation results, the method also includes: in response to receiving a form modification request, modifying the recommendation results included in the form to be filled to obtain actual filling results; evaluating and optimizing the target algorithm model based on the recommendation results and the actual filling results.

[0115] The form to be filled is filled according to the recommended results to obtain a pre-filled form; the executive body of the embodiment of the present invention notifies the business personnel to review the recommended results included in the pre-filled form to determine whether the pre-filled form meets the business requirements, for example, whether the data format meets the business requirements, whether the data content is accurate, whether there are any missing form fields, etc. If the recommended results do not meet the business requirements, the business personnel need to modify the pre-filled form; after receiving the modification request, the executive body of the embodiment of the present invention modifies the recommended results included in the pre-filled form to obtain actual filling results that meet the business requirements.

[0116] The execution subject of the embodiment of the present invention uses the recommended results and the actual filling results as buried data (after generating the recommended results and the actual filling results, timely obtain the data corresponding to the results), and uniformly stores the recommended results and the actual filling results, for example, uploading them to a big data platform; compares the recommended results and the actual filling results, and evaluates the recommended results, for example, compares the number of different data fields included in the recommended results and the actual filling results, and scores or rates the target algorithm model according to the number of different data fields. When the data field has a weight value (for example, the larger the data volume and the more complex the data, the larger the weight value corresponding to the data field), the difference between the recommended result and the actual filling result is evaluated according to the weight value to obtain the evaluation result of the target algorithm model.

[0117] The execution subject of the embodiment of the present invention inputs the recommendation results and the actual filling results into the target algorithm model, so that the target algorithm model is iteratively trained according to the recommendation results and the actual filling results, thereby improving the accuracy and generation efficiency of the recommendation results.

[0118] Exemplarily, the recommended result is "{'dataField1','dataField2','dataField3','dataField4'}", including 4 data fields, namely "dataField1", "dataField2", "dataField3", and "dataField4"; after the business personnel make modifications, the actual filling result is "{'dataField1','dataField2','dataField3','dataField5'}", including 4 data fields, namely "dataField1", "dataField2", "dataField3", and "dataField5"; the recommended result is compared with the actual filling result, and it is determined that there is a data field "dataField4" in the recommended result that does not meet the business requirements, and the data fields that do not meet the business requirements account for 25% of all data fields. The target algorithm model is scored (out of 10 points) and a score of 7.5 is obtained. The target algorithm model is rated (including 4 levels: excellent, good, medium, and poor), and the result is good.

[0119] Modifying the recommended results to obtain the actual filling results can improve the flexibility and accuracy of form filling. Optimizing the target algorithm model based on the recommended results and the actual filling results can improve the accuracy of the target algorithm model and reduce R&D and maintenance costs.

[0120] Figure 5 FIG. 1 is a schematic diagram of the main process of a method for filling in a form according to a reference embodiment of the present invention. Figure 5 As shown, the form filling method may include:

[0121] Step S501, traversing a preset scene information set, acquiring scene information included in the scene information set, and determining feature arrangement information corresponding to the scene information;

[0122] Step S502, acquiring business data corresponding to the scene information according to the feature arrangement information;

[0123] Step S503, converting the service data according to the feature arrangement information to obtain feature parameters corresponding to the scene information;

[0124] Step S504, storing the scene information in association with the corresponding feature parameters;

[0125] Step S505, in response to receiving the form filling request, parsing the form filling request to obtain target scenario information carried in the form filling request;

[0126] Step S506, acquiring corresponding target feature parameters from a non-relational database storing feature parameters according to the target scene information;

[0127] Step S507: input the target feature parameters into the target algorithm model to obtain a recommendation result, and fill in the form to be filled according to the recommendation result.

[0128] The specific implementation content of the form filling method of the above-mentioned reference embodiment of the present invention has been described in detail in the form filling method described above, so the repeated content will not be described again here.

[0129] Figure 6 FIG. 1 is a schematic diagram of the main flow of a method for filling in a form according to another reference embodiment of the present invention. Figure 6 As shown, the form filling method may include:

[0130] Step S601, traversing a preset scene information set, acquiring scene information included in the scene information set, and determining feature arrangement information corresponding to the scene information;

[0131] Step S602, parsing feature arrangement information to obtain a corresponding remote call interface;

[0132] Step S603, using a remote call interface to asynchronously obtain business data corresponding to the scenario information from a preset business data set;

[0133] Step S604, parsing the feature arrangement information to obtain corresponding field mapping relationships and field dependency relationships;

[0134] Step S605, converting the business data according to the field mapping relationship and the field dependency relationship to obtain feature parameters corresponding to the scene information;

[0135] Step S606, storing the scene information in association with the corresponding feature parameters;

[0136] Step S607, in response to receiving the form filling request, parsing the form filling request to obtain target scenario information carried in the form filling request;

[0137] Step S608, acquiring corresponding target feature parameters from a non-relational database storing feature parameters according to the target scene information;

[0138] Step S609, inputting the target feature parameters into the target algorithm model to obtain a recommendation result, and filling the form to be filled according to the recommendation result;

[0139] Step S610, in response to receiving the form modification request, modifying the recommended results included in the form to be filled to obtain actual filling results;

[0140] Step S611, evaluating the target algorithm model according to the recommendation results and the actual filling results.

[0141] The specific implementation content of the form filling method of another reference embodiment of the present invention has been described in detail in the form filling method described above, so the repeated content will not be described again here.

[0142] Figure 7 FIG. 2 is a schematic diagram of the main flow of a method for filling in a form according to another reference embodiment of the present invention. Figure 7 As shown, the form filling method may include:

[0143] Step S701, using the message middleware to asynchronously receive the business data of multiple business domains, and extracting and encapsulating the business data of the multiple business domains;

[0144] Step S702, storing the business data after data extraction and data packaging into the business data set;

[0145] Step S703, traversing the preset scene information set, acquiring the scene information included in the scene information set, and determining the feature arrangement information corresponding to the scene information;

[0146] Step S704, parsing the feature arrangement information to obtain the corresponding remote call interface;

[0147] Step S705, asynchronously obtaining the business data corresponding to the scene information from the business data set using the remote call interface;

[0148] Step S706, parsing the feature arrangement information to obtain corresponding field mapping relationships and field dependency relationships;

[0149] Step S707, converting the business data according to the field mapping relationship and the field dependency relationship to obtain feature parameters corresponding to the scene information;

[0150] Step S708, storing the scene information in association with the corresponding feature parameters;

[0151] Step S709, in response to receiving the form filling request, parsing the form filling request to obtain target scenario information carried in the form filling request;

[0152] Step S710, acquiring corresponding target feature parameters from a non-relational database storing feature parameters according to target scene information;

[0153] Step S711, obtaining a corresponding model identifier according to the target scene information, and determining a target algorithm model from a preset algorithm model set according to the model identifier;

[0154] Step S712, inputting the target feature parameters into the target algorithm model to obtain a recommendation result, and filling the form to be filled according to the recommendation result;

[0155] Step S713, in response to receiving the form modification request, modifying the recommended results included in the form to be filled to obtain actual filling results;

[0156] Step S714, evaluating the target algorithm model according to the recommendation results and the actual filling results;

[0157] Step S715, input the recommendation results and the actual filling results into the target algorithm model, so that the target algorithm model is iteratively trained according to the recommendation results and the actual filling results.

[0158] The specific implementation content of the form filling method of another reference embodiment of the present invention has been described in detail in the form filling method described above, so the repeated content will not be described here.

[0159] According to a second aspect of an embodiment of the present invention, a form filling device is provided.

[0160] Figure 8 is a schematic diagram of the main modules of the form filling device according to an embodiment of the present invention, such as Figure 8 As shown, the form filling device 800 mainly includes:

[0161] A determination module 801 is used to determine target scene information corresponding to the form to be filled in response to receiving a form filling request;

[0162] An acquisition module 802 is used to acquire corresponding target feature parameters according to the target scene information;

[0163] The filling module 803 is used to input the target feature parameters into the target algorithm model to obtain a recommendation result, and fill the form to be filled according to the recommendation result.

[0164] According to a reference embodiment of the present invention, the form filling device 800 further includes:

[0165] A traversal module, used to traverse a preset scene information set, obtain scene information included in the scene information set, and determine feature arrangement information corresponding to the scene information;

[0166] An acquisition module, used for acquiring business data corresponding to the scene information according to the feature arrangement information;

[0167] A conversion module, used to convert the business data according to the feature arrangement information to obtain feature parameters corresponding to the scene information;

[0168] The storage module is used to store the scene information in association with the corresponding feature parameters.

[0169] According to another reference embodiment of the present invention, converting the service data according to the feature arrangement information includes:

[0170] Parsing the feature arrangement information to obtain corresponding field mapping relationships and field dependency relationships;

[0171] The business data is converted according to the field mapping relationship and the field dependency relationship.

[0172] According to another reference embodiment of the present invention, obtaining the service data corresponding to the scene information according to the feature arrangement information includes:

[0173] Parsing the feature arrangement information to obtain a corresponding remote call interface;

[0174] The remote call interface is used to asynchronously obtain the business data corresponding to the scenario information from a preset business data set.

[0175] According to another reference embodiment of the present invention, the form filling device 800 further includes:

[0176] The encapsulation module is used to asynchronously receive business data of multiple business domains using the message middleware, extract and encapsulate the business data of the multiple business domains, and store the business data after data extraction and data encapsulation into the business data set.

[0177] According to another reference embodiment of the present invention, the form filling device 800 further includes:

[0178] An identification module, used to obtain a corresponding model identifier according to the target scene information;

[0179] The determination module is used to determine the target algorithm model from a preset algorithm model set according to the model identifier.

[0180] According to a reference embodiment of the present invention, the form filling device 800 further includes:

[0181] A modification module, configured to modify the recommended results included in the form to be filled in response to receiving a form modification request, to obtain an actual filling result;

[0182] An optimization module is used to evaluate and optimize the target algorithm model according to the recommendation result and the actual filling result.

[0183] It should be noted that the specific implementation content of the form filling device in the embodiment of the present invention has been described in detail in the form filling method described above, so the repeated content will not be described again here.

[0184] According to the technical solution of the embodiment of the present invention, the scenario information corresponding to the form to be filled is determined, the corresponding feature parameters are obtained according to the scenario information, and the recommended results of the form to be filled are generated according to the feature parameters. This can be applicable to the form filling process in various business scenarios, improve the efficiency of form filling, and reduce labor costs; pre-set feature arrangement information corresponding to the scenario information, and convert business data into feature parameters according to the feature arrangement information, which can improve the correlation between feature parameters and scenario information. The feature arrangement information includes business data mapping relationships of various business scenarios, which can associate business data of various business scenarios and improve the flexibility of form filling; converting business data according to field mapping relationships and field dependency relationships can improve the conversion efficiency and accuracy of business data and maintain the dependency and correlation between business data; using remote The program calls the interface to asynchronously obtain business data, which can improve the efficiency of obtaining business data and avoid blocking the filling process of other forms; extracting and encapsulating business data can improve the conversion efficiency and accuracy of business data, ensure that business data complies with the conversion rules, and thus improve the efficiency and accuracy of form filling; determine the corresponding model identifier according to the scenario information of the form to be filled, and determine the target algorithm model corresponding to the form to be filled according to the model identifier, so as to use the corresponding algorithm model according to different business scenarios, and improve the accuracy, flexibility and scalability of form filling; modify the recommended results to obtain the actual filling results, which can improve the flexibility and accuracy of form filling, and optimize the target algorithm model according to the recommended results and the actual filling results, so as to improve the accuracy of the target algorithm model and reduce R&D costs and maintenance costs.

[0185] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for form filling, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided by the first aspect of the embodiment of the present invention.

[0186] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0187] Fig. 9 An exemplary system architecture 900 is shown to which the form filling method or form filling apparatus according to an embodiment of the present invention can be applied.

[0188] like Fig. 9As shown, system architecture 900 may include terminal devices 901, 902, 903, network 904 and server 905. Network 904 is used to provide a medium for communication links between terminal devices 901, 902, 903 and server 905. Network 904 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0189] The user can use the terminal devices 901, 902, 903 to interact with the server 905 through the network 904 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 901, 902, 903, such as form filling applications, form display applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0190] The terminal devices 901 , 902 , and 903 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0191] The server 905 may be a server that provides various services, such as a background management server (only an example) that provides support for form filling requests sent by the upstream terminal devices 901, 902, and 903. In response to receiving the form filling request, the background management server may determine the target scene information corresponding to the form to be filled; obtain the corresponding target feature parameters according to the target scene information; input the target feature parameters into the target algorithm model to obtain the recommendation result, fill the form to be filled according to the recommendation result; and feed back the form filling situation (only an example) to the terminal device.

[0192] It should be noted that the form filling method provided in the embodiment of the present invention is generally executed by the server 905, and accordingly, the form filling device is generally set in the server 905. The form filling method provided in the embodiment of the present invention can also be executed by the terminal devices 901, 902, and 903, and accordingly, the form filling device can be set in the terminal devices 901, 902, and 903.

[0193] It should be understood that Fig. 9 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0194] Reference below Fig.10 , which shows a schematic diagram of the structure of a computer system 1000 of a terminal device suitable for implementing an embodiment of the present invention. Fig.10 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0195] like Fig.10 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the system 1000 are also stored. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0196] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed.

[0197] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the central processing unit (CPU) 1001, the above-mentioned functions defined in the system of the embodiment of the present invention are executed.

[0198] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In an embodiment of the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0199] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0200] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor, for example, they may be described as: a processor includes a determination module, an acquisition module, and a filling module, wherein the names of these modules do not constitute a limitation on the modules themselves under certain circumstances, for example, the determination module may also be described as a "module for determining target scene information corresponding to the form to be filled in".

[0201] As another aspect, an embodiment of the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device implements the following method: in response to receiving a form filling request, determining the target scene information corresponding to the form to be filled; obtaining the corresponding target feature parameters according to the target scene information; inputting the target feature parameters into the target algorithm model to obtain a recommendation result, and filling the form to be filled according to the recommendation result.

[0202] According to the technical solution of the embodiment of the present invention, the scenario information corresponding to the form to be filled is determined, the corresponding feature parameters are obtained according to the scenario information, and the recommended results of the form to be filled are generated according to the feature parameters. This can be applicable to the form filling process in various business scenarios, improve the efficiency of form filling, and reduce labor costs; pre-set feature arrangement information corresponding to the scenario information, and convert business data into feature parameters according to the feature arrangement information, which can improve the correlation between feature parameters and scenario information. The feature arrangement information includes business data mapping relationships of various business scenarios, which can associate business data of various business scenarios and improve the flexibility of form filling; converting business data according to field mapping relationships and field dependency relationships can improve the conversion efficiency and accuracy of business data and maintain the dependency and correlation between business data; using remote The program calls the interface to asynchronously obtain business data, which can improve the efficiency of obtaining business data and avoid blocking the filling process of other forms; extracting and encapsulating business data can improve the conversion efficiency and accuracy of business data, ensure that business data complies with the conversion rules, and thus improve the efficiency and accuracy of form filling; determine the corresponding model identifier according to the scenario information of the form to be filled, and determine the target algorithm model corresponding to the form to be filled according to the model identifier, so as to use the corresponding algorithm model according to different business scenarios, and improve the accuracy, flexibility and scalability of form filling; modify the recommended results to obtain the actual filling results, which can improve the flexibility and accuracy of form filling, and optimize the target algorithm model according to the recommended results and the actual filling results, so as to improve the accuracy of the target algorithm model and reduce R&D costs and maintenance costs.

[0203] The above specific implementations do not constitute a limitation on the protection scope of the embodiments of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. A form filling method, characterized in that: include: In response to receiving the form filling request, determining target scene information corresponding to the form to be filled; Acquire corresponding target feature parameters according to the target scene information; The target feature parameters are input into a target algorithm model to obtain a recommendation result, and the form to be filled is filled according to the recommendation result.

2. The method according to claim 1, characterized in that: Before acquiring corresponding target feature parameters according to the target scene information, the method further includes: Traversing a preset scene information set, acquiring scene information included in the scene information set, and determining feature arrangement information corresponding to the scene information; Acquire the business data corresponding to the scene information according to the feature arrangement information; Convert the service data according to the feature arrangement information to obtain feature parameters corresponding to the scene information; The scene information is associated with the corresponding characteristic parameters and stored.

3. The method according to claim 2, characterized in that The business data is converted according to the feature arrangement information, including: Parsing the feature arrangement information to obtain corresponding field mapping relationships and field dependency relationships; The business data is converted according to the field mapping relationship and the field dependency relationship.

4. The method according to claim 2, characterized in that: Acquiring business data corresponding to the scenario information according to the feature arrangement information includes: Parsing the feature arrangement information to obtain a corresponding remote call interface; The remote call interface is used to asynchronously obtain the business data corresponding to the scenario information from a preset business data set.

5. The method according to claim 4, characterized in that Before asynchronously acquiring the business data corresponding to the scenario information from a preset business data set using the remote call interface, the method further includes: Use message middleware to asynchronously receive business data of multiple business domains, extract and encapsulate the business data of the multiple business domains, and store the business data that has undergone data extraction and data encapsulation into a business data set.

6. The method according to claim 1, characterized in that Before inputting the target feature parameters into the target algorithm model, the method further includes: Acquire a corresponding model identifier according to the target scene information; The target algorithm model is determined from a preset algorithm model set according to the model identifier.

7. The method according to claim 1, characterized in that After filling the to-be-filled form according to the recommendation result, the method further includes: In response to receiving the form modification request, modifying the recommended results included in the form to be filled in to obtain an actual filling result; The target algorithm model is evaluated and optimized according to the recommendation result and the actual filling result.

8. A form filling device, characterized in that: include: A determination module, configured to determine target scene information corresponding to the form to be filled in response to receiving a form filling request; An acquisition module, used to acquire corresponding target feature parameters according to the target scene information; The filling module is used to input the target feature parameters into the target algorithm model to obtain a recommendation result, and fill the form to be filled according to the recommendation result.

9. An electronic device, characterized in that: include: One or more processors; A storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images