Screening condition creation method, system and equipment, storage medium and program product

Abstract

The invention discloses a screening condition creation method, system and device, a storage medium and a program product, and the method comprises the steps that a server side receives a screening condition creation request sent by a client side, and the screening condition creation request comprises a description text of a to-be-created first screening condition; the description text comprises first description information of the target object screened by the first screening condition; and calling a pre-trained large language model, determining a screening script according to the first description information and a preset screening field set, and determining a screening condition formed by the screening script as a first screening condition. According to the invention, automatic creation of the screening condition is realized, and the creation efficiency of the screening condition is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and specifically to a screening condition creation method, system, device, storage medium and program product. Background Art

[0002] In the food delivery scenario, the attendance quality of the riders affects the delivery quality of the orders. In order to facilitate the management of the attendance of each rider and the delivery of the orders, the attendance system is currently used to record the online time, number of completed orders and other data of each rider. When managers want to filter target data, such as filtering the current attendance riders or other required data, they first need to manually download the data from the attendance system into a table, and then manually write the filtering conditions according to the format specified in the table based on the attributes of the target data and other information, so as to filter the data based on the manually written filtering conditions. Alternatively, it is necessary to manually write the filtering code based on the attributes of the target data and other information, so as to filter the data according to the filtering conditions defined in the filtering code.

[0003] However, whether the filtering conditions are manually written or the filtering codes are manually written, the efficiency of creating the filtering conditions is low because the filtering conditions are created manually. Furthermore, when the filtering conditions are complex, the manually created filtering conditions will inevitably lead to inaccurate filtering conditions due to the omission of a sub-condition or the error in the logical relationship between individual sub-conditions. In other words, the accuracy of the filtering conditions is difficult to be effectively guaranteed. Summary of the invention

[0004] In order to solve the problems of low efficiency and difficulty in ensuring accuracy in creating screening conditions in the above-mentioned related technologies, the present application provides a screening condition creation method, system, device, storage medium and program product.

[0005] A first aspect of the present application provides a method for creating a screening condition, which is applied to a server, and the method includes:

[0006] Receive a screening condition creation request sent by a client, the screening condition creation request including a description text of a first screening condition to be created, the description text including first description information of a target object screened by the first screening condition;

[0007] Call the pre-trained large language model to determine the screening script according to the first description information of the target object and the preset screening field set;

[0008] The screening condition formed by the screening script is determined as the first screening condition.

[0009] A second aspect of the present application provides a method for creating a screening condition, which is applied to a client, and the method includes:

[0010] Receiving a description text input by a user through a filtering condition editing interface, the description text including first description information of a target object filtered by a first filtering condition to be created;

[0011] According to the description text, a filtering condition creation request is sent to the server; the filtering condition creation request is used to request the server to call a pre-trained large language model, determine a filtering script according to the first description information of the target object and a preset filtering field set, and determine the filtering condition formed by the filtering script as the first filtering condition.

[0012] A third aspect of the present application provides a screening condition creation device, which is applied to a server, and the device includes:

[0013] A receiving module, configured to receive a request for creating a filtering condition sent by a client, wherein the request for creating a filtering condition includes a description text of a first filtering condition to be created, wherein the description text includes first description information of a target object filtered by the first filtering condition;

[0014] A calling module, used to call a pre-trained large language model and determine a screening script according to the first description information of the target object and a preset screening field set;

[0015] The determination module is used to determine the screening condition formed by the screening script as the first screening condition.

[0016] A fourth aspect of the present application provides a screening condition creation device, which is applied to a client, and the device includes:

[0017] A receiving module, used to receive a description text input by a user through a filtering condition editing interface, wherein the description text includes first description information of a target object filtered by a first filtering condition to be created;

[0018] The sending module is used to send a filtering condition creation request to the server according to the description text; the filtering condition creation request is used to request the server to call a pre-trained large language model, determine a filtering script according to the first description information of the target object and a preset filtering field set, and determine the filtering condition formed by the filtering script as the first filtering condition.

[0019] A fifth aspect of the present application provides a screening condition creation system, the system comprising: a client and a server;

[0020] The client is used to receive a description text input by a user through a filtering condition editing interface, the description text including first description information of a target object filtered by a first filtering condition to be created; and send a filtering condition creation request to a server according to the description text;

[0021] The server is used to receive a request for creating a filtering condition sent by a client; call a pre-trained large language model to determine a filtering script according to the first description information of the target object and a preset filtering field set; and determine the filtering condition formed by the filtering script as the first filtering condition.

[0022] The sixth aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in the first aspect above, or to implement the method described in the second aspect above.

[0023] The seventh aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the method as described in the first aspect above, or to implement the method as described in the second aspect above.

[0024] An eighth aspect of the present application provides a computer program product, including a computer program, wherein the computer program is executed by a processor to implement the method described in the first aspect above, or to implement the method described in the second aspect above.

[0025] Based on the screening condition creation method provided in the first aspect above, the present application has at least the following beneficial effects or advantages:

[0026] In an embodiment of the present application, when the server receives a request to create a screening condition sent by the client, it calls a pre-trained large language model, determines a screening script according to the first description information of the target object and a preset screening field set included in the request to create the screening condition, and determines the screening condition formed by the screening script as the first screening condition. Thus, the user only needs to provide the description information of the screening condition, and the pre-trained large language model can be used to generate the screening script through the online interaction between the client and the server, thereby obtaining the first screening condition. There is no need for the user to manually write the screening condition or the user to manually write the screening code. Therefore, not only the automatic generation of the screening script is realized, that is, the automatic creation of the first screening condition is realized, and the efficiency of creating the screening condition is improved. Moreover, the risk of screening condition errors caused by human writing errors is avoided, which is conducive to improving the accuracy of the screening conditions.

[0027] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0029] Figure 1 This is a first schematic diagram of a screening condition editing interface in the prior art;

[0030] Figure 2 This is a second schematic diagram of a screening condition editing interface in the prior art;

[0031] Figure 3 A schematic diagram of an application scenario of a method for creating a screening condition provided in an embodiment of the present application;

[0032] Figure 4 A first flow chart of a method for creating a screening condition provided in an embodiment of the present application;

[0033] Figure 5 A second flow chart of a method for creating a screening condition provided in an embodiment of the present application;

[0034] Figure 6 A third flow chart of a method for creating a screening condition provided in an embodiment of the present application;

[0035] Figure 7 A fourth flow chart of a method for creating a screening condition provided in an embodiment of the present application;

[0036] Figure 8 A fifth flow chart of a method for creating a screening condition provided in an embodiment of the present application;

[0037] Fig. 9 A fifth flow chart of a method for creating a screening condition provided in an embodiment of the present application;

[0038] Fig.10 A sixth flow chart of a method for creating a screening condition provided in an embodiment of the present application;

[0039] Fig.11 A schematic diagram of a screening interface provided in an embodiment of the present application;

[0040] Fig.12 A schematic diagram of a screening condition editing interface provided in an embodiment of the present application;

[0041] Fig.13 A schematic diagram of a setting interface for screening conditions provided in an embodiment of the present application;

[0042] Fig.14 A seventh flow chart of a method for creating a screening condition provided in an embodiment of the present application;

[0043] Fig.15 An eighth flow chart of a method for creating a screening condition provided in an embodiment of the present application;

[0044] Fig.16 A first structural schematic diagram of a screening condition creation device provided in an embodiment of the present application;

[0045] Fig.17 A second structural schematic diagram of a screening condition creation device provided in an embodiment of the present application;

[0046] Fig.18 A schematic diagram of the composition of a screening condition creation system provided in an embodiment of the present application;

[0047] Fig.19 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0049] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following explanations:

[0050] Filtering script: An automated script program to perform data filtering tasks.

[0051] Large Language Model (LLM): usually refers to a highly complex artificial intelligence model trained using a large amount of data, especially in the field of Natural Language Processing (NLP). The model can understand and generate human language and perform multiple language tasks such as translation, summarization, question answering, data generation, etc.

[0052] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0053] It should be understood that, although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination", etc.

[0054] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0055] Data screening is to filter out data that meets the specified screening conditions in a database or data system. In view of the fact that the current creation of screening conditions requires a lot of manual operations, the creation efficiency of screening conditions is low. In addition, when the screening conditions are more complex, manual creation of screening conditions may lead to inaccurate screening conditions due to the omission of a sub-condition or the error in the logical relationship between individual sub-conditions. A method of customizing screening conditions is proposed in the related art, that is, users can create custom screening conditions in the form of Figure 1 In the custom interface shown, edit the value of each field, and then confirm the new control to save the defined filtering conditions. However, this method requires the custom interface to provide all the fields that can be filtered, so the development cost of the custom interface is high. In addition, since the custom interface includes a large number of fields, users need to select the target field that meets their own filtering needs from a large number of fields, and the user experience is not good. Furthermore, the given range of some fields may not meet the user's filtering needs, such as Figure 1 The range of delivery distance given in the data is 0-999999km, but if the user wants to filter data with a distance greater than 20km, it cannot be defined. In addition, the logical relationship between multiple fields is relatively fixed, either an or logical relationship, or an and logical relationship. When the user needs to define a filter condition containing "and" and "or", it cannot be implemented. Another way to customize the filter condition in the related art is as follows Figure 2In the rule tree-based definition method shown, users can select the required tags in the tag selection part and define the logical relationship between the selected tags through the condition combination part to achieve the definition of complex logical relationships. However, this method requires all tags available for filtering, so there are also problems of high development costs and poor user experience. In addition, developers need to spend time to understand the rules configured by users and write codes manually, so the efficiency of creating filtering conditions is low.

[0056] Based on this, the present application embodiment provides a method for creating a screening condition. Figure 3 Schematic diagram of an application scenario of a method for creating a screening condition provided in an embodiment of the present application. Figure 3 As shown, the scenario includes a client and a server.

[0057] The client can be a terminal device such as a mobile phone, tablet computer, desktop computer, portable notebook, wearable device, etc. The client can install and run the creation application of the screening condition. The creation application can be an independent application (Application, App for short), a small program embedded in other applications, or a web application.

[0058] The client is integrated with a display screen, which is configured to display the user interface (UI) of the client, and provides an interface for interaction and information exchange between the client and the user. The UI involved in the embodiment of the present application can be configured as a medium interface for user operation to interact with the created application. As an interactive interface with the user, the UI can convert the computer language of the created application into a form that the user can accept and recognize, including displayed pictures, text, buttons, etc. The commonly used form of UI can be a graphical user interface (GUI), which refers to a user interface related to computer operation displayed in a graphical manner. It can be an interface element such as an icon, window, control, etc. displayed in the display screen of the client, wherein the control can include visual interface elements such as icons, buttons, menus, tabs, text boxes, etc. The control can be implemented as a visual function interface for creating an application. When the control receives the corresponding trigger operation of the user, the corresponding function interface of the created application receives the corresponding processing instruction, so that the created application responds to the processing instruction for functional processing. For example, each editing operation of the user inputs a corresponding instruction to the created application through the control of the corresponding GUI, thereby triggering the creation program to perform related processing, and updating the GUI based on the processed result.

[0059] The server can be an independent server such as a physical server or a cloud server, or a server cluster composed of multiple servers. The server can maintain a preset filter field set, a pre-trained large language module, a filter script determination strategy, a first filter condition determination strategy, etc. Among them, the filter script determination strategy is used to indicate that when receiving a filter condition creation request sent by the client, the pre-trained large language model is called, and the filter script is determined according to the filter condition creation request and the preset filter field set. The first filter condition determination strategy is used to indicate that the filter condition formed by the determined filter script is determined as the first filter condition. Among them, the first description information is used to describe the target object filtered by the first filter condition.

[0060] The client and the server can exchange data based on the network, which can be a wired network or a wireless network. For the data exchange between the client and the server, please refer to the relevant description below.

[0061] It should be understood that Figure 3 The client is a desktop computer and the server is an independent physical server. Figure 3 The illustration is only a schematic representation of the application scenario of the screening condition creation method involved in the present application, and does not constitute a limitation on the technical solution of the present application. In some other implementations, the application scenario of the screening condition creation method involved in the present application may also include more or fewer components.

[0062] It can be seen that the user only needs to provide the description information of the filtering conditions, and then the pre-trained large language model can be used to generate the filtering script through the online interaction between the client and the server, thereby obtaining the first filtering condition. There is no need for the user to manually write the filtering conditions, nor is there any need for the user to manually write the filtering code. Therefore, not only the automatic generation of the filtering script is realized, that is, the automatic creation of the first filtering condition is realized, and the efficiency of creating the filtering condition is improved. It also avoids the risk of filtering condition errors caused by human writing errors, which is conducive to improving the accuracy of the filtering conditions.

[0063] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The several specific embodiments listed can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0064] Figure 4 A flowchart of a method for creating screening conditions provided in an embodiment of the present application, Figure 4 The method shown can be Figure 3 The server in the implementation. Figure 3 As shown, the method includes the following steps 101-103.

[0065] Step 101: receiving a request for creating a filtering condition sent by a client, wherein the request for creating the filtering condition includes a description text of a first filtering condition to be created, wherein the description text includes first description information of a target object filtered by the first filtering condition.

[0066] Step 102: call a pre-trained large language model and determine a screening script according to the first description information of the target object and a preset screening field set.

[0067] Step 103: determine the screening condition formed by the screening script as the first screening condition.

[0068] In some embodiments, a creation application is installed in the user's client, and the creation application can be used to add, delete, modify, check and other operations on the filtering conditions. The creation application can also be used to perform operations such as data filtering based on the filtering conditions. Specifically, when the user has a data filtering demand, the user can operate the client to input an opening instruction of the creation application. In response to the received opening instruction, the client opens the creation application and displays the filtering interface. When the filtering condition viewing instruction is received through the filtering interface, the identification of each created filtering condition is displayed for the user to select the identification of the required filtering condition. When the user determines that the identification of each filtering condition displayed by the client does not contain the identification of the required filtering condition, the required filtering condition can be created by inputting a new instruction, that is, creating a first filtering condition. Correspondingly, when the client receives the new instruction input by the user through the filtering interface, the filtering condition editing interface is displayed, the description text input by the user through the filtering condition editing interface is received, and a filtering condition creation request is sent to the server according to the description text. Among them, the description text includes the first description information of the target object filtered by the first filtering condition, the identification of the first filtering condition and other information. The target object may vary with different data screening scenarios, that is, with different data types in a preset database, and the preset database is used for data screening operations.

[0069] As an example, the data screening scenario is a takeaway scenario, and the preset database includes each rider's scheduling data, attendance time, number of completed orders, order information (such as order time, ordered goods, order number, etc.), responsible business district range, etc. Correspondingly, the target object can be any one or more of schedule, date, attendance time, number of completed orders, product type, attendance time, geographic location, order number, etc. For example, the target object is the schedule and the number of completed orders, and the first descriptive information can be a full-day schedule and the number of completed orders is greater than 8. For the data types and target objects in the preset database, they will not be listed one by one in this application. They can be set according to needs in actual applications, and this is not specifically limited in this application.

[0070] In order to improve the efficiency of creating filtering conditions and avoid excessive manual operations, thereby improving the efficiency of data screening, in an embodiment of the present application, the data screening scenario (such as a takeaway scenario) is pre-combined, and the description information and the filter field set of each target object corresponding to the data screening scenario are used to fine-tune the large language model, so that the trained large language model can learn the relevant knowledge of determining the filtering script based on the description information and the filter field set. Therefore, when the server receives the filtering condition creation request sent by the client, the pre-trained large language model is called, and the filtering script is determined according to the first description information of the target object included in the filtering condition creation request and the preset filter field set, and the filtering condition corresponding to the filtering script is determined as the first filtering condition. Among them, the fine-tuning training process of the large language model can refer to the relevant technology, and this application does not make specific limitations on this.

[0071] In the screening condition creation method provided in the embodiment of the present application, when the server receives the screening condition creation request sent by the client, it calls the pre-trained large language model, determines the screening script according to the first description information of the target object and the preset screening field set included in the screening condition creation request; and, in response to the confirmation information that the screening script matches the first description information, determines the screening condition formed by the screening script as the first screening condition. Thus, the user only needs to provide the description information of the screening condition, and the pre-trained large language model can be used to generate the screening script through the online interaction between the client and the server, so as to obtain the first screening condition. There is no need for the user to manually write the screening condition, nor is there a need for the user to manually write the screening code. Therefore, not only the automatic generation of the screening script is realized, that is, the automatic creation of the first screening condition is realized, and the efficiency of creating the screening condition is improved. And it avoids the risk of screening condition errors caused by human writing errors, which is conducive to improving the accuracy of the screening conditions.

[0072] Considering that the large language model has rich language processing capabilities, in order to ensure that the large language model generates accurate screening scripts, in some embodiments, prompt information is first generated to indicate the rule for determining the screening script according to the first description information and the preset screening field set, and the screening script is determined using the large language model based on the prompt information. Specifically, Figure 5 As shown, step 102 includes the following steps 1021 and 1022:

[0073] Step 1021, fill the first description information into a preset prompt word template to obtain prompt information; the prompt information is used to instruct the large language model to determine a rule for filtering scripts according to the first description information and a preset filtering field set.

[0074] The preset filter field set includes a plurality of filter fields for filtering data and second description information of each filter field. In some embodiments, the preset prompt word template may be in the following form:

[0075] Please match the conditions entered by the user with the fields in the field list given below, and convert the conditions entered by the user into conditional statements that meet the XXX syntax.

[0076] Field list: XXX.

[0077] User input: XXX.

[0078] Where XXX represents the content to be filled, which can be set according to actual needs in actual applications. As an example, the syntax is array.filter in JavaScript, where array.filter is part of the array method and is used to filter elements in an array that meet a given condition. As another example, the syntax is the WHERE clause in SQL, which allows conditions to be specified, and only records that meet these conditions will be selected and returned.

[0079] The field list in the prompt word template is used to fill in the preset filter field set. When the data filtering scenario is unique, the preset filter field set can also be pre-filled into the XXX position corresponding to the field list. When the data filtering scenario is not unique, for example, the preset database includes data for multiple scenarios, the correspondence between the data filtering scenario and the filter field set can be pre-set. Correspondingly, the filter condition creation request can also include the scene identifier of the data filtering scenario. In step 1021, the server can query the corresponding filter field set according to the scene identifier, and fill the filter field set and the first description information into the preset prompt word template to obtain the prompt information.

[0080] As an example, the data filtering scenario is a takeaway scenario, and some of the filtering fields in the preset filtering field set and the second description information of the filtering fields are as follows:

[0081] scheduled:{desc:'Whether the time period is scheduled', type:'boolean'};

[0082] todayScheduled:{desc:'Whether to schedule for the whole day', type:'boolean'};

[0083] workStatus:{

[0084] desc:'Working status',

[0085] type:'enum 1: work, 2: short break, 3: off work, 4: apply for short break, 5: apply for off work',

[0086] };

[0087] deliveryOrder:{desc:'delivery order quantity', type:'number'};

[0088] fullDayOnlineTime:{desc:'Full-day online time (seconds)', type:'number'};

[0089] fullDayFinishOrder:{desc:'Total number of orders completed during the day', type:'number'};

[0090] timeOnlineTime:{desc:'Online duration of the period (seconds)', type:'number'};

[0091] timeFinishOrder:{desc:'Quantity of orders completed during this period', type:'number'}.

[0092] Among them, taking scheduled:{desc:'Whether the time period is scheduled', type:'boolean'} as an example, the filter field is scheduled, and the second description information of the filter field scheduled is whether the time period is scheduled, and boolean indicates that the type of the field value is Boolean type. Similarly, other filter fields and the second description information of the filter fields can be obtained, which will not be listed one by one in this application.

[0093] The user input in the prompt word template is used to fill in the first description information of the target object. For example, the first description information of the target object is: time period shift attendance, time period completed orders = 0, and 0 orders being delivered during the time period.

[0094] It should be pointed out that the prompt word template is not limited to the above-mentioned form, and it can be set according to actual needs in actual applications, and this application does not make any specific limitation on this.

[0095] Step 1022, input the prompt information into the large language model to obtain a screening script.

[0096] Specifically, the prompt information is input into the large language model, the large language model determines the screening script according to the rules indicated by the prompt information, and outputs the screening script.

[0097] By generating prompt information and inputting the prompt information into the large language model, the prompt information can be used to inform the large language model of the rules for determining the screening script, thereby ensuring the accuracy of the determined screening script.

[0098] In order to accurately convert the first description information of the target object into a screening script, in some embodiments, such as Figure 6 As shown, step 1022 may include the following steps 1022-1 to 1022-3:

[0099] Step 1022 - 1 , input the prompt information into the large language model, and determine the target screening field in the screening field set hit by the first description information of the target object through the large language model.

[0100] Among them, determining that the first description information of the target object hits the target filtering field in the filtering field set may include: for any filtering field in the filtering field set, matching the first description information of the target object with the second description information of the filtering field, and if the match is successful, determining that the filtering field is the hit target filtering field.

[0101] In some embodiments, matching the first description information of the target object with the second description information of the screening field may include: segmenting the first description information of the target object according to a preset segmentation rule to obtain multiple sub-description information, and for each sub-description information, determining the similarity between the sub-description information and the first description information of the screening field, if the similarity is greater than a preset similarity threshold, determining that the match is successful. Among them, the preset segmentation rule can be segmentation based on punctuation marks, or segmentation based on semantics. The similarity can be any one of cosine distance, Euclidean distance, etc. The matching process of the first description information and the second description information is not limited to the above process, which can be set by itself as needed in actual applications, and is not specifically limited in this application.

[0102] Continuing with the example of the above preset filter field set, the first description information of the target object is: time period scheduling attendance, time period completed orders = 0, 0 orders in delivery during the time period, then the target filter fields determined to be hit are scheduled, timeFinishOrder, and deliveryOrder.

[0103] Step 1022 - 2 , obtaining field information of the target screening field from the first description information through the large language model.

[0104] The field information may include at least one of a field value, an operator, etc.

[0105] Continuing with the above example, for the target filtering field scheduled, the field information obtained from the first description information is that the field value is yes, and the operator is equal to; for the target filtering field timeFinishOrder, the field information obtained from the first description information is that the field value is 0, and the operator is equal to; for the target filtering field deliveryOrder, the field information obtained from the first description information is that the field value is 0, and the operator is equal to.

[0106] Step 1022-3, using a large language model to generate a screening script based on the target screening fields and field information according to a preset grammar.

[0107] Specifically, when the number of target screening fields is one, the target screening field and field information are filled into the corresponding position in the preset syntax to obtain a screening script. When the number of target screening fields is multiple, for any target screening field, the target screening field and field information are filled into the corresponding position in the preset syntax to obtain a screening code corresponding to the target screening field; according to the first description information, the combination relationship between the target screening fields in the first screening condition is determined; using the combination symbol corresponding to the combination relationship, the screening codes corresponding to the target screening fields are combined to obtain a screening script.

[0108] Among them, filling the target screening field and field information into the corresponding position in the preset syntax may include: determining whether the field information contains the third description information in the preset mapping relationship, wherein the preset mapping relationship is a mapping relationship between multiple syntax elements in the preset syntax and their third description information. If the field information contains the third description information in the preset mapping relationship, the field information is converted into a syntax element corresponding to the corresponding third description information; and the target screening field and the converted syntax element are filled into the corresponding position of the preset syntax. Among them, the conversion of the field information may be to convert part of the information in the field information, or to convert all of the information in the field information.

[0109] In some implementations, some of the mapping relationships in the preset mapping relationship are exemplified as follows:

[0110] '>=': 'greater than or equal to';

[0111] '<=': 'less than or equal to';

[0112] '===':'equal to';

[0113] '! ==':'Not equal to';

[0114] '&&':'and';

[0115] '||': 'or';

[0116] '>': 'greater than';

[0117] '<': 'less than';

[0118] '!':'no';

[0119] 'true':'yes';

[0120] 'false':'no'.

[0121] In some embodiments, the preset syntax is array.filter in JavaScript, and the syntax format of the target filtering field can be "item.target filtering field operator field value". Continuing with the above example, there are multiple target filtering fields, and the combination relationship between the target filtering fields is determined to be "and" according to the first description information, that is, they need to be satisfied at the same time. Then for the target filtering field scheduled, determine that its field information "field value is yes, operator is equal to" meets the conversion condition, and convert the field value to true, and convert the operator to ===, fill the target filtering field and the conversion result into the preset syntax to obtain the corresponding filtering code item.scheduled === true. Similarly, for the target filtering field timeFinishOrder, the corresponding filtering code item.timeFinishOrder === 0 is obtained; for the target filtering field deliveryOrder, the corresponding filtering code item.deliveryOrder === 0 is obtained; the combination symbol corresponding to the combination relationship is &&, and the obtained filtering script is:

[0122] item.scheduled===true&&item.timeFinishOrder===0&&item.deliveryOrde r===0.

[0123] By determining the target filter field that the description text hits in the preset filter field, and generating a filter script based on the target filter field and its field information according to the preset syntax, the accuracy of the filter script is guaranteed, which provides a guarantee for the accurate filter data of the subsequent execution of the filter script. At the same time, based on the number of target filter fields, the filter script is generated in different ways to ensure that the generated filter script matches the first description information, that is, the accuracy of the filter script is improved.

[0124] Considering that in actual applications, the amount of data in the preset database used for data screening may be large, running the screening script by the client to perform the screening operation may bring greater data processing pressure to the client. Based on this, in some embodiments, the aforementioned preset grammar may be a grammar applicable to the server, such as SQL grammar, etc., and the server maintains the screening script and performs the screening operation based on the screening script. Correspondingly, considering that in actual applications, the first description information of the target object input by the user through the client may contain ambiguity, in order to avoid the screening conditions formed by the screening script determined in this case being different from the actual screening intention of the user, thereby causing problems such as inaccurate screening results based on the screening script filtering data. In some embodiments, the screening script is also converted into a text to be confirmed for the user to confirm. Specifically, if Figure 7 As shown, step 103 may include the following steps 1031 to 1033:

[0125] Step 1031, converting the screening script into a text to be confirmed, where the text to be confirmed is used to describe the screening conditions formed by the screening script.

[0126] Specifically, for any grammatical element in the screening script, the target description text corresponding to the grammatical element is obtained from a preset field set or a preset mapping relationship, and the target description texts corresponding to each grammatical element in the screening script are spliced ​​to obtain the text to be confirmed.

[0127] Continuing with the above example, for the grammatical element item.scheduled in the filtering script item.scheduled===true&&item.timeFinishOrder===0&&item.deliveryOrder===0, its corresponding target description text (i.e., the second description text) is obtained from the preset field set as whether the time period is scheduled, and for the grammatical element ===, its corresponding target description text (i.e., the third description text) is obtained from the preset mapping relationship as equal, and so on. The target description text corresponding to each grammatical element can be obtained, and the text to be confirmed obtained by splicing the target description texts corresponding to each grammatical element is: whether the time period is scheduled is equal to yes, and the number of orders completed in the time period is equal to 0, and the number of orders in delivery is equal to 0.

[0128] Step 1032, sending the text to be confirmed to the client, and receiving confirmation information sent by the client.

[0129] When the client receives the text to be confirmed, it displays the text to be confirmed, and when obtaining the user's confirmation instruction, it sends confirmation information corresponding to the confirmation instruction to the server.

[0130] Step 1033: In response to the confirmation information, determine the screening condition formed by the screening script as the first screening condition.

[0131] By converting the screening script into a text to be confirmed and sending the text to be confirmed to the client for confirmation, the consistency of the screening condition formed by the screening script and the first screening condition is ensured, thereby ensuring the accuracy of subsequent screening data based on the screening script.

[0132] In the case where the server maintains the filtering script and performs the filtering operation based on the filtering script, in order to facilitate the user to trigger the filtering instruction, in some embodiments, when the client receives the user's confirmation instruction based on the text to be confirmed, or when the client receives the creation success information sent by the server, the identifier of the first filtering condition is added to the identifier list. And, when the client receives the filtering instruction input by the user based on the identifier of the first filtering condition in the selected identifier list, a filtering request is sent to the server according to the identifier of the first filtering condition. Correspondingly, Figure 8 As shown, after step 103, the method further includes the following steps 104 and 105:

[0133] Step 104: according to the screening request sent by the client, run the screening script to screen the data in the preset database to obtain the target data.

[0134] In order to enable the server to quickly query the screening script corresponding to the first screening condition when receiving the screening request, in some embodiments, after step 103, it may also include: reading the identifier of the first screening condition from the description information, establishing a corresponding relationship between the screening script and the identifier of the first screening condition, and saving the corresponding relationship. Correspondingly, step 104 may include: querying the corresponding relationship according to the identifier of the first screening condition included in the screening request, running the screening script in the queried corresponding relationship, and filtering the data in the preset database to obtain the target data.

[0135] In some implementations, after the server saves the corresponding relationship, it can also send a creation success message to the client according to the identifier of the first screening condition. Correspondingly, the client displays prompt information indicating that the creation is successful.

[0136] In order to ensure the effective execution of data screening, in some embodiments, a screening function template is preset, and a screening function is determined according to a screening script and a preset screening function template, so as to call the screening function to screen the data. That is, the above-mentioned running of the screening script to screen the data in the preset database to obtain the target data may include: filling the screening script into the preset screening function template to obtain the screening function; calling the screening function to screen the data in the preset database to obtain the target data. Among them, the preset screening function template can be set according to the actual application as needed.

[0137] Step 105, sending the target data to the client.

[0138] When the client receives the target data, it displays the target data.

[0139] It can be seen that after the user creates the first filtering condition, when there is a need for data filtering, the user only needs to operate the client to select the identifier of the first filtering condition, and the corresponding filtering script can be run through the server to perform the filtering operation, without the need for the user to manually edit the filtering condition, thus greatly improving the efficiency of data filtering. Furthermore, since the server saves the filtering script of the first filtering condition, when the user has the same filtering need at different times, they only need to operate the client to select the identifier of the first filtering condition, and the filtering operation can be performed through the same filtering script, which improves the reuse rate of the filtering script.

[0140] Considering that in actual applications, the amount of data in the preset database may not be large, at this time, the client running the screening script to perform the screening operation can further improve the data screening efficiency. Based on this, in some embodiments, the aforementioned preset syntax can be a syntax suitable for the client, such as JS syntax, etc., and the client maintains the screening script and performs the screening operation based on the screening script. Correspondingly, Fig. 9 As shown, after step 103, the following step 106 may be further included:

[0141] Step 106, sending a creation success message to the client based on the identifier of the first filtering condition included in the filtering script and the description text; the creation success message is used to instruct the client to convert the filtering script into a text to be confirmed and display it, and when receiving the confirmation instruction input by the user, establish a corresponding relationship between the filtering script and the identifier of the first filtering condition, and when receiving the filtering instruction input by the user based on the identifier of the first filtering condition, run the filtering script in the corresponding relationship to filter the data to be filtered obtained from the server to obtain the target data.

[0142] The data to be screened may be obtained by the client from the server when the application is created and started, or may be obtained by the client from the server when the screening instruction is received. In some implementations, the client may send a data acquisition request to the server, and the server sends the data in the preset database to the client; the client determines the received data as the data to be screened.

[0143] Therefore, the server sends the filtering script to the client, so that the client can run the corresponding filtering script to perform the filtering operation when it receives the user's filtering instruction, without the need for the client to interact with the server for data. Therefore, the time taken for data interaction between the client and the server is avoided, that is, the processing time of the filtering instruction is shortened, which can further improve the data filtering efficiency.

[0144] Corresponding to the above-mentioned embodiment of the method for creating a screening condition, the present application also provides an embodiment of the method for creating a screening condition. Fig.10 A flowchart of a method for creating screening conditions provided in an embodiment of the present application, Fig.10 The method shown can be Figure 3 The client executes in Fig.10 As shown, the method includes the following steps 201 and 202.

[0145] Step 201: receiving a description text input by a user through a filtering condition editing interface, wherein the description text includes first description information of a target object filtered by a first filtering condition to be created.

[0146] Step 202, based on the description text, sends a filtering condition creation request to the server; the filtering condition creation request is used to request the server to call a pre-trained large language model, determine a filtering script based on the first description information of the target object and a preset filtering field set, and determine the filtering condition formed by the filtering script as the first filtering condition.

[0147] In some implementations, the client includes a screening interface, and the screening interface includes at least one of a new adding interface, a selection interface, and a setting interface. Fig.11 As shown, the filtering interface includes a new control, a selection control, a setting control, a reset control and a detailed list of data. The detailed list may include N fields, where N is an integer greater than 1. Among them, the new control, the selection control, the setting control and the reset control correspond to the new interface, the selection interface, the setting interface and the reset interface respectively. The new interface is used to receive the new instruction, the selection interface is used to receive the selection instruction and display the identification of the filtering condition selected by the user, the setting interface is used to receive the setting instruction, the reset interface is used to receive the reset instruction, and the reset instruction is used to indicate the display of the initial filtering interface. Accordingly, the description text input by the user received through the filtering condition editing interface in step 201 may include:

[0148] In response to a new adding instruction input by a user through a new adding interface, a filtering condition editing interface is displayed; and a description text input by a user through an editing interface of the filtering condition editing interface is received.

[0149] That is, when the user wants to create the first filter condition, he can operate his client to input the opening instruction of the creation application. In response to the received opening instruction, the client opens the creation application and displays the filter interface. The user operates (for example, single-clicks or double-clicks) the new control in the filter interface to input the new instruction. Correspondingly, the client responds to the new instruction input by the user through the new interface corresponding to the new control and opens the filter condition editing interface. Fig.12As shown, the filter condition editing interface includes a first input control for the identification of the filter condition, a second input control for the description information of the target object, a parsing control, a display box for the parsing result, a confirmation control, a cancel control, etc. Among them, the first input control and the second input control correspond to the editing interface, and after the user enters the corresponding information in the first input control and the second input control, the parsing control can be operated. Accordingly, the client receives the description text entered by the user through the editing interface of the filter condition editing interface in response to the parsing instruction input by the user operating the parsing control.

[0150] Considering that in actual applications, the user may modify the filter condition created by the user to obtain a new filter condition. Based on this, in some embodiments, it is also possible to jump from the filter interface to the filter condition setting interface, and then jump from the setting interface to the filter condition editing interface. Specifically, the description text input by the user received through the filter condition editing interface in step 201 may include:

[0151] In response to a selection instruction input by the user through the selection interface of the filtering interface, the first filtering condition corresponding to the selection instruction is displayed at a preset position of the filtering interface; in response to a setting instruction input by the user through the setting interface, the setting interface of the first filtering condition is displayed; if an editing instruction is received from the user through the editing interface contained in the setting interface, the filtering condition editing interface is displayed; and a description text input by the user through the editing interface of the filtering condition editing interface is received.

[0152] In some implementations, the user can place the mouse Fig.11 In the selection control included in the filtering interface shown, the user can operate (for example, single-click or double-click, etc.) the selection control; when the client detects the mouse placement information in the selection control, or responds to the user's operation on the selection control, the client displays the identifiers of each filtering condition included in the identifier list in the drop-down list corresponding to the selection control for the user to select. Each identifier of the filtering condition corresponds to a selection interface. When the user selects the identifier of the first filtering condition from the displayed identifiers, the client responds to the selection instruction input by the user through the selection interface corresponding to the identifier of the first filtering condition, and displays the first filtering condition corresponding to the selection instruction in the selection control of the filtering interface. Alternatively, the filtering interface may also include an identifier display area ( Fig.11(not shown in the figure), the identifiers of each filtering condition included in the identifier list can be displayed in the display area, and each filtering condition identifier corresponds to a selection interface. The user can operate the mouse to select the identifier of the first filtering condition in the display area, and the client responds to the selection instruction input by the user through the selection interface corresponding to the identifier of the first filtering condition, and displays the identifier of the first filtering condition corresponding to the selection instruction in the selection control of the filtering interface. Afterwards, the user can operate the setting control in the filtering interface to jump to the setting interface of the first filtering condition. Accordingly, the client responds to the setting instruction input by the user through the setting interface corresponding to the setting control, and displays the setting interface of the first filtering condition. Fig.13 As shown, the setting interface includes a display control, an edit control, and a delete control. Among them, the display control is used to display the filter condition selected by the user; the edit control corresponds to the edit interface, which is used by the user to input the edit instruction, thereby jumping to the filter condition edit interface; the delete control corresponds to the delete interface, which is used by the user to delete the selected filter condition. Correspondingly, if the client receives the edit instruction input by the user through the edit interface included in the setting interface, the filter condition edit interface is displayed; and the description text input by the user through the edit interface of the filter condition edit interface is received.

[0153] Among them, the process of receiving the description text input by the user through the editing interface of the filtering condition editing interface can be referred to the relevant description in the previous text, and the repeated parts will not be repeated here. The identification list includes the identification of each filtering condition to which the user has access rights. The filtering conditions to which the user has access rights may include filtering conditions created by the user himself, and may also include filtering conditions created by other users but granted access rights to the user. The method of displaying each identification in the filtering list in the filtering interface is not limited to the above form, and it can be set by oneself according to needs in actual application.

[0154] according to Fig.12 It can be seen that in the filter condition editing interface provided in the embodiment of the present application, complex logical relationships can be edited without providing all the fields or tags available for filtering. Figure 1 and Figure 2 The filter condition editing interface shown in the present application greatly reduces the development cost of the filter condition editing interface, avoids the problem that the given range of some fields cannot meet the user's filtering needs. And for users, since there is no need to select between many fields or tags, the user experience can be improved.

[0155] Furthermore, after the client displays the setting interface of the first filtering condition, the method may also include: if a deletion instruction is received from the user through the deletion interface included in the setting interface, a deletion request is sent to the server according to the identifier of the saved first filtering condition; the deletion request is used to request the server to query the target correspondence relationship containing the identifier of the first filtering condition, and delete the target correspondence relationship; and, when a deletion success message is received from the server, the saved identifier of the first filtering condition is deleted.

[0156] Therefore, by providing a new interface in the filtering interface, the user can input a new instruction through the new interface to create the first filtering condition. By providing a selection interface and a setting interface in the filtering interface, the user can view the identifiers of each filtering condition with access rights through the selection interface, and input a selection instruction to select the identifier of the target filtering condition from the identifiers of each filtering condition with access rights, and input a setting instruction through the setting interface to modify and delete the target filtering condition. That is, the user can conveniently add, delete, modify, and check the filtering conditions.

[0157] Considering that in actual applications, the amount of data in the preset database used for data screening may be large, the client running the screening script to perform the screening operation may bring greater data processing pressure to the client. Based on this, in some implementations, the server maintains the screening script and performs the screening operation based on the screening script. Correspondingly, in order to ensure the accuracy of the screening script, after the server determines the screening script based on the first description information of the target object and the preset screening field set, it also converts the screening script into a text to be confirmed, and sends the text to be confirmed to the client for confirmation. Correspondingly, if Fig.14 As shown, after the client sends a request to create a filter condition to the server, the method further includes:

[0158] Receive and display the text to be confirmed sent by the server, which is used to describe the screening conditions formed by the screening script determined by the server; if a confirmation instruction input by the user is received, the confirmation information corresponding to the confirmation instruction is sent to the server.

[0159] Specifically, after receiving the confirmation text sent by the server, the client can Fig.12 The display control corresponding to the parsing result included in the filtering condition editing interface shown displays the text to be confirmed. When the user determines that the text to be confirmed is consistent with the first filtering condition, the confirmation control in the filtering interface can be operated. Correspondingly, if the client receives a confirmation instruction input by the user operating the confirmation control in the filtering interface, the confirmation information corresponding to the confirmation instruction is sent to the server.

[0160] Continuing with the previous example, Fig.12As shown, the first filter condition entered by the user is identified as "Filter Condition 2", the description information is "Time period scheduling attendance, time period completed orders = 0, time period delivery 0 orders", and the displayed confirmation text is "Whether the time period is scheduled is equal to yes and the time period completed orders are equal to 0 and the delivery orders are equal to 0".

[0161] Furthermore, when the user determines that the text to be confirmed is inconsistent with the first filtering condition, the cancel control in the filtering interface can be operated. Correspondingly, if the client receives a cancel instruction triggered by the user operating the cancel control in the filtering interface, a prompt message is displayed, and the cancel information corresponding to the cancel instruction is sent to the server. The prompt message is used to prompt the user to re-enter the description text, and when the server receives the cancel information sent by the client, it deletes the corresponding filtering script.

[0162] Therefore, by receiving and displaying the text to be confirmed sent by the server so that the user can confirm the text to be confirmed, and sending confirmation information corresponding to the confirmation instruction triggered by the user to the server, the accuracy of the screening script determined by the server is guaranteed, that is, the accuracy of the first screening condition formed by the screening script is guaranteed.

[0163] When the server maintains the filtering script and performs filtering operations based on the filtering script, in order to facilitate users to filter data, such as Fig.14 As shown, after the client receives the confirmation instruction input by the user based on the text to be confirmed, the following may also be included:

[0164] Add the identifier of the first filtering condition to the identifier list; and, if a filtering instruction input by the user based on the identifier of the first filtering condition in the identifier list is received, send a filtering request to the server according to the identifier of the first filtering condition; receive the target data sent by the server and display the target data, wherein the target data is obtained by the server running a filtering script to filter the data in a preset database.

[0165] In some embodiments, when the user selects an identifier corresponding to the first filtering condition from among the identifiers in the identifier list displayed on the filtering interface, the filtering instruction can be triggered through the selection interface at the same time. In other embodiments, the filtering interface can also include a filtering control corresponding to the filtering interface ( Fig.11(not shown), after the client displays each identifier in the identifier list through the filtering interface, in response to the user's selection operation on the identifier corresponding to the first filtering condition, the identifier of the first filtering condition is displayed in the selection control of the filtering interface; and when the filtering instruction input by the user through the filtering control (i.e., the filtering interface) is obtained, a filtering request is sent to the server according to the identifier of the first filtering condition. The server runs the filtering script according to the filtering request to filter the data in the preset database, obtains the target data, and sends the target data to the client. The client receives the target data sent by the server and displays the target data in the detailed list part of the filtering interface. Among them, the specific process of displaying each identifier in the identifier list in the filtering interface can be found in the relevant description in the previous text, and the repeated parts will not be repeated here.

[0166] Furthermore, after receiving the confirmation instruction input by the user based on the text to be confirmed, the client may also display prompt information indicating successful creation.

[0167] It can be seen that after creating the first filtering condition, when the user has a filtering requirement based on the first filtering condition, there is no need to edit the first filtering condition again, and the user only needs to select the corresponding mark in the marks of each filtering condition displayed on the client. Therefore, the data filtering efficiency is greatly improved.

[0168] Considering that in actual applications, the amount of data in the preset database may not be large, at this time, the client performing the screening operation can further improve the data screening efficiency. Based on this, in some implementations, the client can maintain the screening script and perform the screening operation based on the screening script. Specifically, Fig.15 As shown, after the client sends a request to create a filter condition to the server, the method may further include:

[0169] Receive the creation success information sent by the server, and obtain the identification of the filtering script and the first filtering condition from the creation success information; convert the filtering script into a text to be confirmed, and display the text to be confirmed; when receiving a confirmation instruction input by the user, add the identification of the first filtering condition to the identification list, establish a corresponding relationship between the filtering script and the identification of the first filtering condition, and save the corresponding relationship; if a filtering instruction input by the user based on the identification of the first filtering condition in the identification list is received, query the corresponding relationship according to the identification of the first filtering condition, run the filtering script in the corresponding relationship to filter the data to be filtered obtained from the server to obtain the target data, and display the target data;

[0170] Among them, the text to be confirmed is used to describe the screening conditions formed by the screening script. When the client maintains the screening script, the mapping relationship between the multiple grammatical elements in the aforementioned preset grammar and its third description information can be maintained by the client to convert the screening script into the text to be confirmed according to the mapping relationship. The process by which the client converts the screening script into the text to be confirmed is the same as the process by which the server converts the screening script into the text to be confirmed, and reference can be made to the relevant description above. The specific process of inputting the screening instruction can also be found in the relevant description above, and the repeated parts will not be repeated here.

[0171] The data to be screened can be obtained by the client from the server when the application is created and started; or it can be obtained by the client from the server when the screening instruction is received. In some implementations, the client can send a data acquisition request to the server, and the server sends the data in the preset database to the client; the client determines the received data as the data to be screened.

[0172] Running the screening script in the corresponding relationship to screen the data in the preset database to obtain the target data may include: filling the screening script in the corresponding relationship into the preset screening function template to obtain the screening function; calling the screening function to screen the data in the preset database to obtain the target data.

[0173] In some implementations, the preset screening function template may be in the following form:

[0174]

[0175]

[0176] Among them, ${js} is the filtering script that needs to be filled in. It should be pointed out that the preset filtering function template is not limited to the above form, and it can be set according to the actual application needs.

[0177] Furthermore, when receiving the confirmation instruction input by the user, the client may also display a prompt message indicating that the creation is successful.

[0178] Therefore, the server sends the filtering script to the client, so that the client can run the corresponding filtering script to perform the filtering operation when it receives the user's filtering instruction, without the need for the client to interact with the server for data. Therefore, the time taken for data interaction between the client and the server is avoided, that is, the processing time of the filtering instruction is shortened, which can further improve the data filtering efficiency.

[0179] It should be pointed out that Figures 11 to 13 The interface shown is not limited thereto and can be set as required in actual applications. Fig.14 and Fig.15For the specific implementation methods of each step, please refer to the relevant description in the previous text, and the repeated parts will not be repeated here. Fig.14 and Fig.15 For illustration only and not for limitation, the execution order of some operations can be interchanged, some operations can be executed simultaneously, and more or fewer operation steps can be included. For example, Fig.14 After step 1-10, the server may also send a creation success message to the client, and correspondingly, in step 1-8, adding the identifier of the first screening condition to the identifier list may be performed after receiving the creation success message sent by the server.

[0180] It can be seen that after creating the first filtering condition, when the user has a filtering requirement based on the first filtering condition, there is no need to edit the first filtering condition again, and the user only needs to select the corresponding mark in the marks of each filtering condition displayed on the client. Therefore, the data filtering efficiency is greatly improved.

[0181] Corresponding to the above-mentioned embodiment of the method for creating a screening condition, the present application also provides an embodiment of a device for creating a screening condition. Fig.16 FIG. 1 is a schematic diagram showing a structure of a device for creating a screening condition according to an exemplary embodiment. The device can be configured to Figure 3 The device is used to execute the filtering condition creation method applied to the server provided in any of the above embodiments, such as Fig.16 As shown, the screening condition creation device includes:

[0182] The receiving module 301 is used to receive a filtering condition creation request sent by a client, wherein the filtering condition creation request includes a description text of a first filtering condition to be created, wherein the description text includes first description information of a target object filtered by the first filtering condition.

[0183] The calling module 302 is used to call the pre-trained large language model and determine the screening script according to the first description information of the target object and the preset screening field set.

[0184] The determination module 303 is used to determine the screening condition formed by the screening script as the first screening condition.

[0185] In some implementations, the calling module 302 is specifically configured to:

[0186] The first description information is filled into a preset prompt word template to obtain prompt information; the prompt information is used to instruct the large language model to determine a rule for filtering the script according to the first description information and a preset filtering field set.

[0187] Input the prompt information into the large language model to obtain the screening script.

[0188] In some implementations, the calling module 302 is specifically configured to:

[0189] A target filter field hit by the first description information of the target object in a filter field set is determined, where the filter field set includes a plurality of filter fields for filtering data.

[0190] The field information of the target screening field is obtained from the first description information.

[0191] Generate a filtering script based on the target filtering fields and field information according to the preset syntax.

[0192] In some implementations, the calling module 302 is further specifically configured to:

[0193] When the number of target screening fields is one, the target screening field and field information are filled into corresponding positions in the preset syntax to obtain a screening script.

[0194] When there are multiple target filtering fields, for any target filtering field, fill the target filtering field and field information into the corresponding position in the preset syntax to obtain the filtering code corresponding to the target filtering field; determine the combination relationship between the target filtering fields in the first filtering condition based on the first description information; use the combination symbol corresponding to the combination relationship to combine the filtering codes corresponding to the target filtering fields to obtain the filtering script.

[0195] In some embodiments, the device further includes a conversion module and a first sending module.

[0196] The conversion module is used to convert the screening script into a text to be confirmed before the determination module 303 determines the screening condition formed by the screening script as the first screening condition, and the text to be confirmed is used to describe the screening condition formed by the screening script.

[0197] The first sending module is used to send the text to be confirmed to the client.

[0198] The receiving module 301 is further used to receive confirmation information sent by the client.

[0199] In some embodiments, the device further includes a screening module and a second sending module.

[0200] The receiving module 301 is further configured to receive a screening request sent by a client after the determining module 303 determines the screening condition formed by the screening script as the first screening condition.

[0201] The filtering module is used to run the filtering script to filter the data in the preset database to obtain the target data according to the filtering request.

[0202] The second sending module is used to send the target data to the client.

[0203] In some embodiments, the screening module is specifically used to:

[0204] Fill the filter script into the preset filter function template to obtain the filter function.

[0205] Call the filtering function to filter the data in the preset database to obtain the target data.

[0206] In some embodiments, the description text further includes an identification of the first screening condition, and the apparatus further includes a establishing module;

[0207] The establishing module is used to establish a corresponding relationship between the screening script and the identifier of the first screening condition after the determining module 303 determines the screening condition formed by the screening script as the first screening condition, and save the corresponding relationship.

[0208] Correspondingly, the screening module is specifically used to obtain the identifier of the first screening condition from the screening request, query the corresponding correspondence according to the identifier of the first screening condition, and run the screening script in the queried correspondence to filter the data in the preset database to obtain the target data.

[0209] In some embodiments, the device further includes a third sending module.

[0210] The third sending module is used to send a creation success message to the client according to the identifiers of the filtering script and the first filtering condition after the determination module 303 determines the filtering condition formed by the filtering script as the first filtering condition; the creation success message is used to instruct the client to convert the filtering script into a text to be confirmed and display it, and when receiving the confirmation instruction input by the user, establish a corresponding relationship between the filtering script and the identifier of the first filtering condition, and when receiving the filtering instruction input by the user based on the identifier of the first filtering condition, run the filtering script in the corresponding relationship to filter the data to be filtered obtained from the server to obtain the target data.

[0211] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are merely schematic, wherein the modules described as separate components may or may not be physically separated, and the components illustrated as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application. A person of ordinary skill in the art may understand and implement it without creative work.

[0212] Corresponding to the above-mentioned embodiment of the method for creating a screening condition, the present application also provides an embodiment of a device for creating a screening condition. Fig.17FIG. 1 is a schematic diagram showing a structure of a device for creating a screening condition according to an exemplary embodiment. The device can be configured to Figure 3 The device is used to execute the method for creating a screening condition applied to a client provided in any of the above embodiments, such as Fig.17 As shown, the screening condition creation device includes:

[0213] The receiving module 401 is used to receive a description text input by a user through a filtering condition editing interface, where the description text includes first description information of a target object filtered by a first filtering condition to be created.

[0214] The sending module 402 is used to send a filtering condition creation request to the server according to the description text; the filtering condition creation request is used to request the server to call a pre-trained large language model, determine a filtering script according to the first description information of the target object and a preset filtering field set, and determine the filtering condition formed by the filtering script as the first filtering condition.

[0215] In some embodiments, the description text also includes an identifier of the first filtering condition, and the device also includes a display module and an adding module.

[0216] The receiving module 401 is further used to receive the to-be-confirmed text sent by the server after the sending module 402 sends the request for creating the screening condition to the server, where the to-be-confirmed text is used to describe the screening condition formed by the screening script.

[0217] The display module is used to display the text to be confirmed.

[0218] The sending module 402 is further configured to send confirmation information corresponding to the confirmation instruction to the server if the receiving module 401 receives a confirmation instruction input by the user.

[0219] The adding module is used to add the identifier of the first screening condition to the identifier list.

[0220] The sending module 402 is further configured to send a filtering request to the server according to the identifier of the first filtering condition when the receiving module 401 receives a filtering instruction input by the user based on the identifier of the first filtering condition in the identifier list.

[0221] The receiving module 401 is also used to receive target data sent by the server, where the target data is obtained by the server running a screening script to screen the data in the preset database.

[0222] The display module is also used to display target data.

[0223] In some implementations, the description text includes an identifier of the first screening condition, and accordingly, the device further includes a conversion module, a saving module, an operation module, and a display module.

[0224] The conversion module is used to convert the screening script into a text to be confirmed, and the text to be confirmed is used to describe the screening conditions formed by the screening script.

[0225] The display module is used to display the text to be confirmed.

[0226] The saving module is used to add the identifier of the first filtering condition to the identifier list, establish a corresponding relationship between the filtering script and the identifier of the first filtering condition, and save the corresponding relationship when the receiving module 401 receives a confirmation instruction input by the user.

[0227] The running module is used to query the corresponding relationship according to the identifier of the first filtering condition if the receiving module 401 receives the filtering instruction input by the user based on the identifier of the first filtering condition in the identifier list, and run the filtering script in the corresponding relationship to filter the data to be filtered obtained from the server to obtain the target data.

[0228] The display module is also used to display target data.

[0229] In some implementations, the client includes a screening interface, the screening interface includes at least one of a new adding interface, a selection interface, and a setting interface, and the device also includes a display module.

[0230] The display module is used to display a filter condition editing interface in response to a new instruction input by a user through a new interface.

[0231] The receiving module 401 is specifically configured to receive creation information input by a user through an editing interface of the screening condition editing interface.

[0232] Alternatively, the display module is used to display the first filtering condition corresponding to the selection instruction at a preset position of the filtering interface in response to a selection instruction input by the user through the selection interface; to display the setting interface of the first filtering condition in response to a setting instruction input by the user through the setting interface; if the receiving module 401 receives an editing instruction input by the user through the editing interface contained in the setting interface, the filtering condition editing interface is displayed.

[0233] The receiving module 401 is further used to receive the creation information input by the user through the editing interface of the screening condition editing interface.

[0234] In some embodiments, the device further comprises a deletion module.

[0235] The sending module 402 is also used to send a deletion request to the server according to the identifier of the saved first filtering condition after the display module displays the setting interface of the first filtering condition. The deletion request is used to request the server to query the target correspondence relationship containing the identifier of the first filtering condition and delete the target correspondence relationship if the receiving module 401 receives a deletion instruction input by the user through the deletion interface contained in the setting interface.

[0236] The deletion module deletes the saved identification when receiving the deletion success information sent by the server.

[0237] The screening condition creation device provided in the embodiment of the present application and the screening condition creation method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented therein.

[0238] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0239] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are merely schematic, wherein the modules described as separate components may or may not be physically separated, and the components illustrated as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application. A person of ordinary skill in the art may understand and implement it without creative work.

[0240] Corresponding to the above-mentioned embodiment of the screening condition creation method, the present application also provides an embodiment of the screening condition creation system. Fig.18 FIG. 1 is a structural diagram of a screening condition creation system according to an exemplary embodiment. Fig.18 As shown, the screening condition creation system includes: a client 501 and a server 502;

[0241] The client 501 is used to receive a description text input by a user through a filtering condition editing interface, the description text including first description information of a target object filtered by a first filtering condition to be created; and send a filtering condition creation request to the server 502 according to the description text;

[0242] The server 502 is used to receive the filtering condition creation request sent by the client 501, call the pre-trained large language model, determine the filtering script according to the first description information of the target object and the preset filtering field set; and determine the filtering condition formed by the filtering script as the first filtering condition.

[0243] The screening condition creation system provided in the embodiment of the present application and the screening condition creation method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented therein.

[0244] It is understandable that the division of the above modules is only a division of logical functions. In actual implementation, the functions of the above modules can be integrated into hardware entities. For example, the functions of the aforementioned receiving module 301, receiving module 401 and sending module 402 can be integrated into a transceiver implementation, and the functions of the calling module 302 and the determining module 303 can be integrated into a processor implementation, etc.

[0245] Based on this, some embodiments of the present application also provide an electronic device corresponding to the screening condition creation method provided in the above-mentioned embodiment, and the electronic device can be configured as follows: Figure 3 The server or client shown is used to execute the above-mentioned filtering condition creation method.

[0246] Fig.19 6 is a hardware structure diagram of an electronic device according to an exemplary embodiment, the electronic device includes: a communication interface 601, a processor 602, a memory 603 and a bus 604; wherein the communication interface 601, the processor 602 and the memory 603 communicate with each other through the bus 604. The processor 602 can execute the above-described method for creating filtering conditions by reading and executing machine executable instructions corresponding to the control logic of the method for creating filtering conditions in the memory 603. The specific content of the method is referred to the above embodiment, which will not be repeated here.

[0247] The memory 603 mentioned in the embodiment of the present application can be any electronic, magnetic, optical or other physical storage device, and can contain storage information, such as executable instructions, data, etc. Specifically, the memory 603 can be RAM (Random Access Memory), flash memory, storage drive (such as hard disk drive), any type of storage disk (such as optical disk, DVD, etc.), or similar storage medium, or a combination thereof. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 601 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0248] The bus 604 may be an ISA bus, a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 603 is used to store programs, and the processor 602 executes the programs after receiving execution instructions.

[0249] Processor 602 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in processor 602 or an instruction in software form. The above-mentioned processor 602 can be a general-purpose processor, including a network processor (Network Processor, referred to as NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware controls, etc. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor are combined to execute.

[0250] The electronic device provided in the embodiment of the present application and the screening condition creation method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented therein.

[0251] An embodiment of the present application also provides a computer-readable storage medium corresponding to the screening condition creation method provided in the aforementioned embodiment, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the screening condition creation method provided in any of the aforementioned embodiments.

[0252] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0253] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the screening condition creation method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0254] An embodiment of the present application also provides a computer program product corresponding to the screening condition creation method provided in the aforementioned embodiment. The computer program product includes a computer program, and the computer program is executed by a processor to implement the screening condition creation method provided in the aforementioned embodiment.

[0255] The computer program product provided by the above-mentioned embodiments of the present application and the screening condition creation method provided by the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0256] The solutions in this application specification and embodiments, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0257] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0258] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0259] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for creating a screening condition, characterized in that: Applied to the server, the method includes: Receive a screening condition creation request sent by a client, wherein the screening condition creation request includes a description text of a first screening condition to be created, wherein the description text includes first description information of a target object screened by the first screening condition; Calling a pre-trained large language model to determine a screening script according to the first description information of the target object and a preset screening field set; The screening condition formed by the screening script is determined as the first screening condition.

2. The method according to claim 1, characterized in that The calling of the pre-trained large language model and determining the screening script according to the first description information of the target object and the preset screening field set include: Filling the first description information into a preset prompt word template to obtain prompt information; the prompt information is used to instruct the large language model to determine a rule for filtering scripts according to the first description information and the preset filtering field set; The prompt information is input into the large language model to obtain a screening script.

3. The method according to claim 1 or 2, characterized in that: The determining of the screening script according to the first description information of the target object and the preset screening field set includes: Determine a target screening field hit by the first description information of the target object in the screening field set; Acquire field information of the target screening field from the first description information; Generate a screening script based on the target screening field and the field information according to a preset syntax.

4. The method according to claim 3, characterized in that The step of generating a screening script from the target screening field and the field information according to a preset syntax includes: In the case where the number of the target screening field is one, filling the target screening field and the field information into corresponding positions in the preset syntax to obtain a screening script; In the case where there are multiple target filtering fields, for any target filtering field, the target filtering field and the field information are filled into the corresponding positions in the preset syntax to obtain the filtering code corresponding to the target filtering field; according to the first description information, the combination relationship between the target filtering fields in the first filtering condition is determined; using the combination symbol corresponding to the combination relationship, the filtering codes corresponding to the target filtering fields are combined to obtain a filtering script.

5. The method according to claim 1, characterized in that Before determining the screening condition formed by the screening script as the first screening condition, the method further includes: Converting the screening script into a text to be confirmed, wherein the text to be confirmed is used to describe the screening condition formed by the screening script; The text to be confirmed is sent to the client, and confirmation information sent by the client is received.

6. The method according to claim 1, characterized in that After determining the screening condition formed by the screening script as the first screening condition, the method further includes: According to the screening request sent by the client, the screening script is run to screen the data in the preset database to obtain the target data; The target data is sent to the client.

7. The method according to claim 6, characterized in that The step of running the screening script to screen the data in the preset database to obtain target data includes: Filling the screening script into a preset screening function template to obtain a screening function; The screening function is called to screen the data in the preset database to obtain the target data.

8. The method according to claim 1, characterized in that The description text further includes an identifier of the first screening condition. After determining the screening condition formed by the screening script as the first screening condition, the method further includes: Based on the screening script and the identifier, a creation success message is sent to the client; the creation success message is used to instruct the client to convert the screening script into a text to be confirmed and display it, and when a confirmation instruction input by the user is received, a corresponding relationship between the screening script and the identifier is established, and when a screening instruction input by the user based on the identifier is received, the screening script in the corresponding relationship is run to filter the data to be screened obtained from the server to obtain the target data.

9. A method for creating a screening condition, characterized in that: Applied to a client, the method comprises: Receiving a description text input by a user through a filtering condition editing interface, the description text including first description information of a target object filtered by a first filtering condition to be created; According to the description text, a filtering condition creation request is sent to the server; the filtering condition creation request is used to request the server to call a pre-trained large language model, determine a filtering script according to the first description information of the target object and a preset filtering field set, and determine the filtering condition formed by the filtering script as the first filtering condition.

10. A screening condition creation system, characterized in that: The system comprises: a client and a server; The client is used to receive a description text input by a user through a screening condition editing interface, wherein the description text includes first description information of a target object screened by a first screening condition to be created; and send a screening condition creation request to the server according to the description text; The server is used to receive the filtering condition creation request sent by the client; call the pre-trained large language model to determine the filtering script according to the first description information of the target object and the preset filtering field set; and determine the filtering condition formed by the filtering script as the first filtering condition.

Images