Text data processing method, system and device and readable storage medium

Abstract

The embodiment of the invention provides a text data processing method, system and device and a readable storage medium, and relates to the technical field of computers. According to the embodiment of the invention, after the preceding text is obtained, at least one associated text corresponding to the preceding text can be determined in the pre-stored associated information, and then at least one following text corresponding to the associated text is determined through the text model stored in the structured database. That is to say, according to the embodiment of the invention, the following text corresponding to the previous text can be quickly determined by calling the pre-stored associated information and the structured database, the steps of manual retrieval, reading understanding, rule interpretation and the like are not needed, the time for determining the following text is shortened, and the reply efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a text data processing method, system, device and readable storage medium. Background Art

[0002] At present, when users receive services provided by the service platform, they will inevitably encounter questions that need to be answered. At this time, users can ask the customer service personnel of the service platform the questions that need to be answered. Correspondingly, the customer service personnel of the service platform need to make corresponding answers based on the questions raised by the users.

[0003] During this process, customer service personnel often need to go through a series of steps such as manual retrieval, reading comprehension, and rule interpretation to query the corresponding answers to questions. However, the above methods consume a lot of time, resulting in low response efficiency. Therefore, how to improve response efficiency is an issue that needs to be urgently addressed. Summary of the invention

[0004] In view of this, embodiments of the present application provide a text data processing method, system, device and readable storage medium to improve reply efficiency.

[0005] In a first aspect, a text data processing method is provided, the method comprising:

[0006] Get the above text.

[0007] At least one associated text corresponding to the above text is determined in the pre-stored associated information, where the associated text is a pre-stored text having at least one associated relationship with the above text.

[0008] The pre-constructed structured database is called by the execution engine, and at least one following text corresponding to the associated text is determined according to the associated text and the text model stored in the structured database.

[0009] Output the following text.

[0010] In some embodiments, the method further comprises:

[0011] Get the original text collection.

[0012] Text modeling is performed on each text in the original text set to generate a text model according to the association relationship between each text in the original text set.

[0013] The text model is stored in the structured database.

[0014] In some embodiments, performing text modeling on each text in the original text set to generate a text model according to the association relationship between each text in the original text set includes:

[0015] The judgment logic corresponding to each text in the original text set is extracted.

[0016] Text modeling is performed according to each text in the original text set and the judgment logic to generate a text model.

[0017] In some embodiments, the method further comprises:

[0018] Get the original text collection.

[0019] Extract keyword information of each text in the original text set.

[0020] Pre-stored association information is created according to at least one association rule, wherein the association rule includes at least task association, time association and activity association, and the pre-stored association information includes each of the keyword information and the association relationship between each of the keyword information.

[0021] The pre-stored association information is stored in an association information database.

[0022] In some embodiments, obtaining the original text set includes:

[0023] The database editing interface is displayed.

[0024] Receive externally input information to be processed, and update the original text set according to the information to be processed.

[0025] In some embodiments, the structured database includes an application layer, a functional layer, and a storage layer.

[0026] The application layer at least includes a database calling interface, the functional layer at least includes a text model management unit, an execution logic unit and an associated information retrieval unit, and the storage layer is at least used to store text models.

[0027] In some embodiments, outputting the following text includes:

[0028] The following text is displayed on the display interface.

[0029] In a second aspect, a text data processing system is provided, the system comprising a calling end and a database end, wherein the database end is used to store a pre-built structured database and pre-stored associated information.

[0030] The calling end is configured to perform the following steps:

[0031] Get the above text.

[0032] At least one associated text corresponding to the above text is determined in the pre-stored associated information through a communication connection with the database end, wherein the associated text is a pre-stored text having at least one associated relationship with the above text.

[0033] The structured database stored in the database end is called by the execution engine, and at least one following text corresponding to the associated text is determined according to the associated text and the text model stored in the structured database.

[0034] Output the following text.

[0035] In some embodiments, the database end includes a structured data end and an associated information end, wherein the structured data end is used to store a pre-built structured database, and the associated information end is used to store pre-stored associated information.

[0036] In a third aspect, a text data processing device is provided, the device comprising:

[0037] The above text acquisition module is configured to execute acquisition of the above text.

[0038] The associated text determination module is configured to determine at least one associated text corresponding to the above text in the pre-stored associated information, wherein the associated text is a pre-stored text having at least one associated relationship with the above text.

[0039] The following text determination module is configured to execute the calling of a pre-built structured database through an execution engine, and determine at least one following text corresponding to the associated text according to the associated text and the text model stored in the structured database.

[0040] The output module is configured to output the following text.

[0041] In some embodiments, the apparatus further comprises:

[0042] The original text set acquisition module is configured to execute acquisition of the original text set.

[0043] The text model generation module is configured to perform text modeling on each text in the original text set, so as to generate a text model according to the association relationship between each text in the original text set.

[0044] The first storage module is configured to store the text model in the structured database.

[0045] In some embodiments, the text model generation module is specifically configured to perform:

[0046] The judgment logic corresponding to each text in the original text set is extracted.

[0047] Text modeling is performed according to each text in the original text set and the judgment logic to generate a text model.

[0048] In some embodiments, the apparatus further comprises:

[0049] The original text set acquisition module is configured to execute acquisition of the original text set.

[0050] The extraction module is configured to extract keyword information of each text in the original text set.

[0051] The pre-stored association information creation module is configured to create pre-stored association information according to at least one association rule, wherein the association rule at least includes task association, time association and activity association, and the pre-stored association information includes each of the keyword information and the association relationship between each of the keyword information.

[0052] The second storage module is configured to execute storage of the pre-stored association information into an association information database.

[0053] In some embodiments, the original text set acquisition module is specifically configured to execute:

[0054] The database editing interface is displayed.

[0055] Receive externally input information to be processed, and update the original text set according to the information to be processed.

[0056] In some embodiments, the structured database includes an application layer, a functional layer, and a storage layer.

[0057] The application layer at least includes a database calling interface, the functional layer at least includes a text model management unit, an execution logic unit and an associated information retrieval unit, and the storage layer is at least used to store text models.

[0058] In some embodiments, the output module is specifically configured to perform:

[0059] The following text is displayed on the display interface.

[0060] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described in the first aspect is implemented.

[0061] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the method described in the first aspect.

[0062] After obtaining the preceding text, the embodiment of the present application can determine at least one associated text corresponding to the preceding text in the pre-stored associated information, and then determine at least one following text corresponding to the associated text through the text model stored in the structured database. In other words, the embodiment of the present application can quickly determine the following text corresponding to the preceding text by calling the pre-stored associated information and the structured database, without the need for manual retrieval, reading comprehension, and rule interpretation, thereby reducing the time for determining the following text and improving the efficiency of reply. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The above and other purposes, features and advantages of the embodiments of the present application will become more apparent through the following description of the embodiments of the present application with reference to the accompanying drawings, in which:

[0064] Figure 1 A schematic diagram of a text data processing system according to an embodiment of the present application;

[0065] Figure 2 A flowchart of a text data processing method according to an embodiment of the present application;

[0066] Figure 3 A flowchart for creating and storing pre-stored association information for an embodiment of the present application;

[0067] Figure 4 A flowchart for generating and storing a text model for an embodiment of the present application;

[0068] Figure 5 A flowchart for generating a text model for an embodiment of the present application;

[0069] Figure 6 A schematic diagram of a database editing interface according to an embodiment of the present application;

[0070] Figure 7 A schematic diagram of a database viewing interface of an embodiment of the present application;

[0071] Figure 8 A schematic diagram of a display interface according to an embodiment of the present application;

[0072] Fig. 9 A schematic diagram of another text data processing system according to an embodiment of the present application;

[0073] Fig.10 A schematic diagram of the structured database of an embodiment of the present application;

[0074] Fig.11A schematic diagram of the structure of a text data processing device according to an embodiment of the present application;

[0075] Fig.12 A schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0076] The present application is described below based on embodiments, but the present application is not limited to these embodiments. In the detailed description of the present application below, some specific details are described in detail. It is possible for those skilled in the art to fully understand the present application without the description of these details. In order to avoid confusing the essence of the present application, known methods, processes, flows, components and circuits are not described in detail.

[0077] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0078] Unless the context clearly requires otherwise, the words "include", "comprising" and the like throughout this application should be interpreted as including rather than exclusive or exhaustive; that is, as meaning "including but not limited to".

[0079] In the description of this application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, "multiple" means two or more. In addition, the schemes described in this specification and the embodiments, if involving the processing of personal information, will be processed on the premise of having a legal basis (for example, with the consent of the subject of personal information, or necessary for the performance of a contract, etc.), and will only be processed within the prescribed or agreed scope. The user's refusal to process personal information other than the necessary information required for basic functions will not affect the user's use of basic functions.

[0080] At present, when users receive online services, offline services, or online and offline services provided by the service platform, they will inevitably encounter questions that need to be answered. At this time, users can ask the customer service personnel of the service platform questions that need to be answered through telephone, Internet, or text messages, and correspondingly, the customer service personnel of the service platform need to make corresponding answers in real time according to the questions raised by users.

[0081] Take online car-hailing services as an example. When users encounter problems such as unavailable coupons, they can call the customer service hotline or ask online customer service to ask the customer service staff why the coupons are unavailable. Furthermore, customer service staff need to go through a series of processes such as manual retrieval, reading comprehension, and rule interpretation to effectively answer the questions raised by users.

[0082] That is to say, when facing questions raised by users, customer service personnel often need to go through a series of steps such as manual search, reading comprehension, and rule interpretation to find the corresponding answers to the questions. However, the above methods will consume a lot of time, resulting in low response efficiency. In one case, if the customer service personnel do not find the corresponding answer, they need to further ask other relevant staff, which further affects the response efficiency. Therefore, how to improve the response efficiency is an urgent problem to be solved.

[0083] In order to solve the above problems, the embodiment of the present application provides a text data processing method and a text data processing system to achieve rapid matching of questions raised by users and improve answering efficiency. The text data processing method of the embodiment of the present application can be applied to the text data processing system, which can include a calling end and a database end.

[0084] like Figure 1 As shown, data can be transmitted between the calling end 11 and the database end 12 by wired connection (such as data line connection, etc.) or wireless connection (such as remote network connection or near field wireless communication connection, etc.). Among them, the database end 12 can be used to store a pre-built structured database and pre-stored associated information.

[0085] Specifically, the structured database of the embodiment of the present application is a database for storing texts and the associations between texts, wherein the associations between texts can be stored in the structured database in the form of a text model. Taking the above customer service scenario as an example, the text model can perform logical operations based on one or more keyword information related to the question and determine one or more pre-stored standard answers corresponding to the question.

[0086] In addition, the pre-stored association information of the embodiment of the present application may include multiple keyword information with association relationships. Taking the above customer service scenario as an example, the keyword information in the pre-stored association information may be the keyword corresponding to the question. When the user asks a question, the embodiment of the present application can determine the corresponding and / or associated keyword information in the pre-stored association information according to the question raised by the user.

[0087] Furthermore, the calling end 11 can determine at least one associated text corresponding to the above text in the pre-stored associated information after obtaining the above text (for example, the question text raised by the user) through the pre-stored associated information and the structured database stored in the database end 12, and then determine at least one following text corresponding to the associated text through the text model stored in the structured database. In other words, the text data processing system of the embodiment of the present application can quickly determine the following text corresponding to the above text through the text data processing method, without the need for manual retrieval, reading comprehension, and rule interpretation, thereby reducing the time for determining the following text and improving the response efficiency.

[0088] Specifically, Figure 2 As shown, the text data processing method of the embodiment of the present application may include the following steps:

[0089] In step S110, the above text is obtained.

[0090] Among them, the above text can be text directly input by the user, or text obtained through voice-to-text conversion, or questions input by customer service personnel. For example, when a user asks a question to the customer service of the service platform, he can directly enter the question he wants to ask through the online customer service platform of the service platform (such as whether there is a carpooling service in this area, the duration of the current promotion, the reason why the coupon is not available, etc.). At this time, the question entered by the user is the above text. For another example, when a user asks a question to the customer service of the service platform, he can also enter a voice message through the online customer service platform of the service platform. After the online customer service platform receives the voice message, it can obtain the text information corresponding to the question through voice-to-text conversion. At this time, the text information corresponding to the question is the above text. For another example, when a user asks a question to the customer service of the service platform, he can also directly ask the question by telephone or other means. At this time, the customer service staff can enter one or more key information (such as carpooling-city-time) as the above text through the question raised by the user.

[0091] In step S120, at least one associated text corresponding to the above text is determined in the pre-stored associated information.

[0092] The associated text is a pre-stored text that has at least one associated relationship with the above text, and the pre-stored associated information may include multiple texts with associated relationships. That is, when a user asks a question, the embodiment of the present application can determine the corresponding and / or associated text in the pre-stored associated information as the associated text according to the question raised by the user.

[0093] For example, if the question raised by the user is "Is there a carpooling service in this area", the embodiment of the present application can determine the associated text based on the question raised by the user, and the associated text may include: carpooling, city / region, start time / end time, etc.

[0094] In an optional embodiment, if Figure 3 As shown, the pre-stored association information in the embodiment of the present application can be determined by the following steps:

[0095] In step S210, an original text set is obtained.

[0096] Among them, the original text collection may include any number of text documents. The embodiment of the present application can obtain hot spot information, business line information and other information related to the service platform itself in a legal manner, and use the above information as a text document in the original text collection.

[0097] In step S220, keyword information of each text in the original text set is extracted.

[0098] Among them, the embodiment of the present application can perform keyword screening processing on each text in the original text set to filter out invalid words, punctuation marks, conjunctions, etc. in the text, and retain words with practical meaning as keyword information.

[0099] In step S230, pre-stored association information is created according to at least one association rule.

[0100] Among them, the pre-stored association information includes each keyword information and the association relationship between each keyword information, and the association rules include at least task association, time association and activity association. Specifically, task association can be used to characterize keywords that are associated with service tasks. For example, keywords that are task-associated with the keyword "coupon" may include "taxi", "express", etc. Time association can be used to characterize keywords that are associated with time. For example, keywords that are time-associated with the keyword "coupon" may include "use period", "validity period", etc. Activity association can be used to characterize keywords that are associated with specific activities. For example, keywords that are activity-associated with the keyword "coupon" may include "XXX activity", "usage conditions", etc. In addition, the association rules of the embodiment of the present application are not limited to the above-mentioned task association, time association and activity association. For example, the association rules of the embodiment of the present application may also include location association, vehicle type association, etc.

[0101] In step S240, the pre-stored association information is stored in the association information database.

[0102] Among them, the associated information database can be used to store pre-stored associated information, which can be set at the database end in the text data processing system. By pre-determining and storing the pre-stored associated information, the embodiment of the present application can quickly determine at least one associated text corresponding to the previous text according to the pre-stored associated information, and then determine at least one following text corresponding to the associated text through the text model stored in the structured database. The following text corresponding to the previous text is quickly determined without the need for manual retrieval, reading comprehension, and rule interpretation, which reduces the time for determining the following text and improves the reply efficiency.

[0103] In step S130, the pre-constructed structured database is called by the execution engine, and at least one following text corresponding to the associated text is determined according to the associated text and the text model stored in the structured database.

[0104] Among them, the following text in the embodiment of the present application is a text that has an associated relationship with the above text. For example, if the above text is a question raised by a user or a question-related text entered by a customer service staff, then the following text is the standard answer corresponding to the question.

[0105] A structured database is a database for storing texts and the relationships between texts. The relationships between texts can be stored in the structured database in the form of a text model. After the embodiment of the present application determines the associated text, the text model can perform a logical operation based on the associated text (i.e., the text related to the user's question) and determine one or more pre-stored standard answers corresponding to the associated text.

[0106] For example, if the associated text determined by the embodiment of the present application includes: carpooling, city / region, start time / end time, the text model can perform business line logic judgment (i.e., determine whether the information stored in the structured database includes the carpooling business line), location logic judgment (i.e., determine whether the information stored in the structured database includes the corresponding city / region) and time logic judgment (i.e., determine whether the information stored in the structured database includes the corresponding time) based on the above associated text, thereby determining at least one subsequent text corresponding to the associated text.

[0107] In an optional embodiment, if Figure 4 As shown, the text model of the embodiment of the present application can be determined by the following steps:

[0108] In step S310, an original text set is obtained.

[0109] Among them, the original text collection may include any number of text documents. The embodiment of the present application can obtain hot spot information, business line information and other information related to the service platform itself in a legal manner, and use the above information as a text document in the original text collection.

[0110] In step S320, text modeling is performed on each text in the original text set to generate a text model according to the association relationship between each text in the original text set.

[0111] Among them, the association relationship between each text can be determined by the judgment logic between each text. That is to say, the embodiment of the present application can generate a text model based on the judgment logic between each text, so that the text model can quickly determine the following text corresponding to the associated text according to the judgment logic, thereby improving the reply efficiency.

[0112] In an optional embodiment, if Figure 5 As shown, the above step S320 may include the following steps:

[0113] In step S321, the judgment logic corresponding to each text in the original text set is extracted.

[0114] Specifically, the judgment logic extracted by the embodiment of the present application may include a judgment type, an input parameter value, and a logical expression. Among them, the judgment type can be used to characterize the type of text, the business line to which it belongs, and other information. For example, the judgment type may include "carpooling", "express", "taxi", "promotional activities", and the like. The input parameter value can be used to characterize the specific content of the text. For example, the input parameter value may include a specific time, a specific place, and the like. The logical expression can be used to characterize the logical judgment process between texts. For example, the logical expression may include ">", "<", "≥", "≤", "=", "≠", "include", "do not include", "like", and the like. These logical expressions can be used in the process of logical judgments such as time judgment, numerical judgment, set judgment, and string judgment.

[0115] In step S322, text modeling is performed according to each text in the original text set and the judgment logic to generate a text model.

[0116] In step S330, the text model is stored in a structured database.

[0117] Among them, the text model can be in the form of a list, table, logical tree, etc. In the process of determining the following text, the embodiment of the present application can call the text model document in the structured database through the execution engine to quickly determine the following text corresponding to the previous text, without the need for manual retrieval, reading comprehension, and rule interpretation, thereby reducing the time for determining the following text and improving the response efficiency.

[0118] In an optional implementation, the process of acquiring the original text set in the embodiment of the present application can be executed as follows: displaying a database editing interface, receiving externally input information to be processed, and updating the original text set according to the information to be processed.

[0119] like Figure 6 As shown, the customer service personnel or relevant staff of the service platform can input the information to be processed through the database editing interface 61, wherein the database editing interface 61 can be the interface displayed by the calling end or the interface displayed by the database end.

[0120] according to Figure 6 It can be seen that the customer service staff or relevant staff of the service platform can input the information to be processed in the information input form 611. Figure 6 For example, the column "Whether to open the corresponding service" in the information input form 611, and the "opened" and "not opened" therein are the pending information entered by the customer service personnel or relevant staff. Figure 6 The information in the information input table 611 can be modified by using the “Add Row”, “Add Column” and “Delete” controls shown, and the name of the information input table 611 can also be set through the “Rule Table Name” column.

[0121] Furthermore, after the information input form 611 is edited, the calling end or the database end may update the original text set according to the information to be processed, and generate a text model and pre-stored associated information based on the updated original text set.

[0122] It should be noted that after the information input form 611 is edited, the customer service staff or relevant staff can open the database editing interface 61 again to update the information input form 611. Further, the embodiment of the present application can also create a template for editing the database to Figure 6 For example, the name of the template can be entered in the "Template" column, and the logical judgment rules can be pre-set in the "Rule" column to avoid repeated entry of logical judgment rules and improve the efficiency of maintaining the database.

[0123] In addition, after editing, the customer service staff or relevant staff of the service platform can also view the saved information input form. Figure 7 As shown in FIG. 7 , the customer service personnel or relevant staff can view the inputted information to be processed through the database viewing interface 71. In the database viewing interface 71, the customer service personnel or relevant staff cannot change the information therein. If the customer service personnel or relevant staff want to change the information displayed in the database viewing interface 71, the customer service personnel or relevant staff can open the following Figure 6 The database editing interface 61 shown is used to modify the corresponding information.

[0124] In step S140, the following text is output.

[0125] Among them, the way of outputting the following text may include text display, voice broadcast and other ways. After acquiring the above text, the embodiment of the present application can determine at least one associated text corresponding to the above text in the pre-stored associated information, and then determine at least one following text corresponding to the associated text through the text model stored in the structured database. In other words, the embodiment of the present application can quickly determine the following text corresponding to the above text by calling the pre-stored associated information and the structured database, without the steps of manual retrieval, reading comprehension and rule interpretation, thereby reducing the time for determining the following text and improving the reply efficiency.

[0126] In an optional implementation, the embodiment of the present application may display the following text on the display interface.

[0127] Take the customer service staff entering the above text as an example. Figure 8 As shown, the customer service staff can enter the above text 811 in the display interface 81 (the above text 811 includes two words "carpooling" and "city A"). Further, the embodiment of the present application can quickly determine the following text 812 corresponding to the above text 811 by calling the pre-stored association information and structured database, wherein the following text 812 can be Figure 8 The list shown can also be presented in other forms such as plain text, table, etc. In this way, the customer service staff can quickly and intuitively view the following text 812 in the display interface 81 without the need for manual retrieval, reading comprehension, and rule interpretation, which reduces the time for determining the following text and improves the efficiency of reply.

[0128] In an optional implementation, the structured database and pre-stored association information of the embodiment of the present application can be stored in different electronic devices respectively. Specifically, the database end of the embodiment of the present application may include a structured data end and an association information end. Among them, the structured data end can be used to store a pre-built structured database, and the association information end can be used to store pre-stored association information, that is, the association information end can be used to store the association information database.

[0129] For example, Fig. 9As shown, the calling end 11 of the embodiment of the present application can be connected to the structured data end 91 and the associated information end 92 respectively by means of a wired connection (such as a data line connection, etc.) or a wireless connection (such as a remote network connection or a near-field wireless communication connection, etc.). In the process of determining the following text, the calling end 11 can first determine at least one associated text corresponding to the above text in the pre-stored associated information through a communication connection with the associated information end 92. Furthermore, the calling end 11 can call the structured database in the structured data end 91 through a communication connection with the structured data end 91, and determine at least one following text corresponding to the associated text based on the associated text and the text model stored in the structured database, so as to output the following text.

[0130] Since the size of structured databases and related information databases will gradually increase with continuous maintenance, Fig. 9 In the system composed of multiple devices shown, the embodiment of the present application can set the structured database and the associated information database in different electronic devices to ensure that each electronic device in the system is not subjected to greater pressure, thereby improving the stability of the system.

[0131] It should be noted that in another optional implementation, the embodiment of the present application can also use an electronic device to simultaneously implement the functions of the calling terminal 11, the structured data terminal 91 and the associated information terminal 92. In other words, the embodiment of the present application can also use a single electronic device to store the structured database and the associated information database, and use the electronic device to determine the following text corresponding to the previous text, thereby avoiding the impact caused by data transmission interruption.

[0132] In an optional implementation, the structured database of the embodiment of the present application may include an application layer, a function layer and a storage layer.

[0133] The application layer at least includes a database calling interface, the functional layer at least includes a text model management unit, an execution logic unit and an associated information retrieval unit, and the storage layer is at least used to store text models.

[0134] For example, Fig.10 As shown, Fig.10 Schematic diagram of the structured database of an embodiment of the present application. Specifically, the application layer 101 may include at least a database call interface, which may be provided to an external device (e.g., a caller) for use, so that the external device can call the information in the structured database. Optionally, the application layer 101 may also include an information search application and an information viewing application to provide corresponding search and viewing functions.

[0135] The functional layer 102 may include at least a text model management unit, an execution logic unit, and an associated information retrieval unit, and these three units may be used for the production application of structured information. For example, the text model management unit may include functions such as template definition, information creation, and information import, the execution logic unit may include a rule engine for processing judgment logic to implement functions such as business logic and rule verification, and the associated information retrieval unit may be used to retrieve master data, metadata, and custom data in the associated information database, which may be used as pre-stored associated information. Optionally, functional units such as online audit, version management, status management, structured audit, and structured information management applications may also be set in the functional layer 102. Among them, the structured information management application may be used to classify and extract data to determine information data of types such as hot information, key information, standard classification, and business line information.

[0136] The storage layer 103 may be used at least to store the text model, wherein the storage layer 103 may include a variety of storage units, such as Fig.10 The relational database management system (MySQL), distributed storage system (Elastic Search, ES), remote dictionary service storage system (Remote Dictionary Server, Redis) and GIFT storage system shown.

[0137] By calling a structured database, the embodiment of the present application can quickly determine the following text corresponding to the associated text after determining at least one associated text corresponding to the previous text, without the need for manual retrieval, reading comprehension, and rule interpretation, thereby reducing the time for determining the following text and improving response efficiency.

[0138] Based on the same technical concept, the embodiment of the present application also provides a text data processing device, such as Fig.11 As shown, the device includes: a preceding text acquisition module 111, a related text determination module 112, a following text determination module 113 and an output module 114.

[0139] The preceding text acquisition module 111 is configured to execute acquisition of preceding text.

[0140] The associated text determination module 112 is configured to determine at least one associated text corresponding to the above text in the pre-stored associated information, where the associated text is a pre-stored text having at least one associated relationship with the above text.

[0141] The following text determination module 113 is configured to execute the calling of a pre-built structured database through an execution engine, and determine at least one following text corresponding to the associated text according to the associated text and the text model stored in the structured database.

[0142] The output module 114 is configured to output the following text.

[0143] In some embodiments, the apparatus further comprises:

[0144] The original text set acquisition module is configured to execute acquisition of the original text set.

[0145] The text model generation module is configured to perform text modeling on each text in the original text set, so as to generate a text model according to the association relationship between each text in the original text set.

[0146] The first storage module is configured to store the text model in the structured database.

[0147] In some embodiments, the text model generation module is specifically configured to perform:

[0148] The judgment logic corresponding to each text in the original text set is extracted.

[0149] Text modeling is performed according to each text in the original text set and the judgment logic to generate a text model.

[0150] In some embodiments, the apparatus further comprises:

[0151] The original text set acquisition module is configured to execute acquisition of the original text set.

[0152] The extraction module is configured to extract keyword information of each text in the original text set.

[0153] The pre-stored association information creation module is configured to create pre-stored association information according to at least one association rule, wherein the association rule at least includes task association, time association and activity association, and the pre-stored association information includes each of the keyword information and the association relationship between each of the keyword information.

[0154] The second storage module is configured to execute storage of the pre-stored association information into an association information database.

[0155] In some embodiments, the original text set acquisition module is specifically configured to execute:

[0156] The database editing interface is displayed.

[0157] Receive externally input information to be processed, and update the original text set according to the information to be processed.

[0158] In some embodiments, the structured database includes an application layer, a functional layer, and a storage layer.

[0159] The application layer at least includes a database calling interface, the functional layer at least includes a text model management unit, an execution logic unit and an associated information retrieval unit, and the storage layer is at least used to store text models.

[0160] In some embodiments, the output module 114 is specifically configured to perform:

[0161] The following text is displayed on the display interface.

[0162] After obtaining the preceding text, the embodiment of the present application can determine at least one associated text corresponding to the preceding text in the pre-stored associated information, and then determine at least one following text corresponding to the associated text through the text model stored in the structured database. In other words, the embodiment of the present application can quickly determine the following text corresponding to the preceding text by calling the pre-stored associated information and the structured database, without the need for manual retrieval, reading comprehension, and rule interpretation, thereby reducing the time for determining the following text and improving the efficiency of reply.

[0163] Fig.12 is a schematic diagram of an electronic device of an embodiment of the present application, the electronic device may be a calling end or a database end in a text data processing system, and further, the electronic device may be a structured data end or an associated information end in a database end. In another case, Fig.12 The electronic device shown may also independently store a structured database and an associated information database, and determine the corresponding context text through the context text.

[0164] like Fig.12 As shown, Fig.12 The electronic device shown is a general address query device, which includes a general computer hardware structure, which at least includes a processor 121 and a memory 122. The processor 121 and the memory 122 are connected via a bus 123. The memory 122 is suitable for storing instructions or programs executable by the processor 121. The processor 121 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 121 executes the instructions stored in the memory 122, thereby executing the method flow of the embodiment of the present application as described above to realize the processing of data and the control of other devices. The bus 123 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 124 and the display device and the input / output (I / O) device 125. The input / output (I / O) device 125 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 125 is connected to the system through an input / output (I / O) controller 126.

[0165] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices (equipment) or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0166] The present application is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0167] These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0168] These computer program instructions may also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0169] Another embodiment of the present application relates to a non-volatile storage medium for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute part or all of the above method embodiments.

[0170] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by specifying relevant hardware through a program, and the program is stored in a storage medium, including several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0171] Another embodiment of the present application relates to a computer program product, including a computer program / instruction, which can implement part or all of the above method embodiments when the computer program / instruction is executed by a processor.

[0172] That is, those skilled in the art can understand that the embodiments of the present application can specify relevant hardware (including the processor itself) through the processor executing a computer program product (computer program / instructions), thereby implementing all or part of the steps in the above-mentioned embodiment method.

[0173] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A text data processing method, characterized in that: The method comprises: Get the above text; Determining at least one associated text corresponding to the above text in the pre-stored associated information, wherein the associated text is a pre-stored text having at least one associated relationship with the above text; Calling a pre-built structured database through an execution engine, and determining at least one following text corresponding to the associated text according to the associated text and a text model stored in the structured database; Output the following text.

2. The method according to claim 1, characterized in that The method further comprises: Get the original text collection; Performing text modeling on each text in the original text set to generate a text model according to the association relationship between each text in the original text set; The text model is stored in the structured database.

3. The method according to claim 2, characterized in that The performing text modeling on each text in the original text set to generate a text model according to the association relationship between each text in the original text set includes: Extracting the judgment logic corresponding to each text in the original text set; Text modeling is performed according to each text in the original text set and the judgment logic to generate a text model.

4. The method according to claim 1, characterized in that: The method further comprises: Get the original text collection; Extracting keyword information of each text in the original text set; Creating pre-stored association information according to at least one association rule, wherein the association rule at least includes task association, time association and activity association, and the pre-stored association information includes each of the keyword information and the association relationship between each of the keyword information; The pre-stored association information is stored in an association information database.

5. The method according to any one of claims 2 to 4, characterized in that: The obtaining of the original text set comprises: Display the database editing interface; Receive externally input information to be processed, and update the original text set according to the information to be processed.

6. The method according to claim 1, characterized in that The structured database includes an application layer, a function layer and a storage layer; The application layer at least includes a database calling interface, the functional layer at least includes a text model management unit, an execution logic unit and an associated information retrieval unit, and the storage layer is at least used to store text models.

7. The method according to claim 1, characterized in that The output of the following text includes: The following text is displayed on the display interface.

8. A text data processing system, characterized in that: The system includes a calling end and a database end, wherein the database end is used to store a pre-built structured database and pre-stored associated information; The calling end is configured to perform the following steps: Get the above text; Determining at least one associated text corresponding to the above text in the pre-stored associated information through a communication connection with the database end, wherein the associated text is a pre-stored text having at least one associated relationship with the above text; Calling the structured database stored in the database end through the execution engine, and determining at least one following text corresponding to the associated text according to the associated text and the text model stored in the structured database; Output the following text.

9. The system according to claim 8, characterized in that The database end includes a structured data end and an associated information end, wherein the structured data end is used to store a pre-built structured database, and the associated information end is used to store pre-stored associated information.

10. A text data processing device, characterized in that: The device comprises: A previous text acquisition module is configured to execute acquisition of the previous text; An associated text determination module is configured to determine at least one associated text corresponding to the above text in the pre-stored associated information, wherein the associated text is a pre-stored text having at least one associated relationship with the above text; A following text determination module is configured to execute a call to a pre-built structured database through an execution engine, and determine at least one following text corresponding to the related text according to the related text and a text model stored in the structured database; The output module is configured to output the following text.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

12. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images