A data processing method, apparatus, device, and medium

Abstract

This application relates to the field of data processing, specifically to a data processing method, apparatus, device, and medium. The method includes: acquiring a question statement; extracting a first keyword and a second keyword from the question statement; wherein the first keyword indicates the business scenario to which the question statement belongs, and the second keyword indicates a specified attribute of the question statement within the business scenario; determining at least one third keyword that has a subordinate relationship with the second keyword based on a reasoning graph corresponding to the business scenario; determining at least one target answer statement corresponding to the question statement, and determining at least one recommended statement including the first keyword and the third keyword based on the first keyword and at least one third keyword; and sending answer information to a user's device; wherein the answer information includes at least one target answer statement and at least one recommended statement.

Description

Technical Field

[0001] This application relates to the field of data processing, specifically to a data processing method, apparatus, device, and medium. Background Technology

[0002] In intelligent question answering, the simple question-and-answer process and limited content of the responses may not fully meet user needs. Therefore, while answering the question, related questions can be recommended to guide the user to ask their own questions, participate in multiple rounds of dialogue, and improve the user experience. In existing technologies, the recommended related questions are often semantically similar to the user's question. For example, if a user asks "What is the definition of a credit card?", since both credit cards and debit cards are bank cards, the recommended related question might be "What is the definition of a debit card?" However, the recommended statements are only semantically similar to the question and may not be truly relevant. This reduces the likelihood of resolving the user's actual needs, resulting in poor intelligence and a poor user experience for the intelligent question answering device. Summary of the Invention

[0003] This application provides a data processing method, apparatus, device, and medium to improve the intelligence of intelligent question-answering devices and enhance user experience.

[0004] In a first aspect, embodiments of this application provide a data processing method, the method comprising:

[0005] Obtain the question statement, and extract a first keyword and a second keyword from the question statement; wherein, the first keyword is used to indicate the business scenario to which the question statement belongs, and the second keyword is used to indicate the specified attribute of the question statement in the business scenario to which it belongs;

[0006] Based on the reasoning graph corresponding to the business scenario, at least one third keyword that has an accessory relationship with the second keyword is determined; wherein, the reasoning graph is used to indicate the accessory relationship between each attribute and other attributes among multiple attributes in the business scenario;

[0007] Determine at least one target answer statement corresponding to the question statement, and determine at least one recommended statement including the first keyword and the third keyword based on the first keyword and the at least one third keyword; wherein, the recommended statement is the question statement composed of the first keyword and the third keyword;

[0008] Send answer information to the user's device; wherein the answer information includes at least one target answer statement and at least one recommended statement.

[0009] In this solution, a first keyword indicating the business scenario to which the question statement belongs and a second keyword indicating the specified attribute of the question statement within its business scenario are determined from the question statement. At least one third keyword with an accessory relationship to the second keyword is determined based on the reasoning graph. At least one recommended statement including the first keyword and the third keyword is determined. In this way, the recommended statement has the same business scenario as the question statement and the correlation between the recommended statement and the question statement is strong, which increases the possibility of users asking questions based on the recommended statement, increases the possibility of solving users' real needs, improves the intelligence of the intelligent question answering device, and enhances the user experience.

[0010] Optionally, before determining at least one third keyword that has an affiliated relationship with the second keyword based on the inference graph corresponding to the business scenario, the method further includes: determining the inference graph corresponding to the business scenario from the multiple candidate inference graphs based on the mapping relationship between a pre-stored set of business scenarios and multiple candidate inference graphs; the set of business scenarios includes the business scenario.

[0011] This method ensures the reliability and rationality of the solution when there are multiple candidate reasoning graphs.

[0012] Optionally, determining at least one third keyword that has an affiliated relationship with the second keyword based on the reasoning graph corresponding to the business scenario includes: determining whether the specified attribute includes at least one sub-attribute based on the reasoning graph corresponding to the business scenario; if the reasoning graph indicates that the specified attribute of the question statement includes at least one sub-attribute based on the business scenario indicated by the first keyword in the question statement, then determining the at least one third keyword based on the at least one sub-attribute.

[0013] This method allows for the determination of at least one third keyword when a specified attribute includes at least one sub-attribute, meaning the attribute can be further subdivided into more detailed sub-attributes. This third keyword, generated in this way, has a strong correlation with the second keyword and can further refine the second keyword, improving the reliability and completeness of the solution. Furthermore, the recommended statement including the third keyword can refine the question statement, increasing the likelihood of users asking questions based on the recommended statement, thus enhancing the user experience.

[0014] Optionally, the method further includes: if the specified attribute does not include any sub-attribute, determining whether the specified attribute has a parent attribute based on the inference graph corresponding to the business scenario; if the specified attribute has a parent attribute, determining the at least one third keyword based on all attributes other than the specified attribute that are divided by the parent attribute of the specified attribute.

[0015] This method allows for the determination of at least one third keyword when a specified attribute does not include any sub-attributes, based on other attributes derived from the parent attribute of the specified attribute. This results in a strong correlation between the generated third keyword and the second keyword, improving the reliability and completeness of the solution. Furthermore, the subsequent recommended statements generated based on the third keyword are highly relevant to the question statements, increasing the likelihood of users asking questions based on the recommended statements, thus enhancing the user experience.

[0016] Optionally, sending the answer information to the user's device includes: obtaining the number of times each third keyword is used to generate a recommended statement; prioritizing the at least one recommended statement according to the number of times the at least one third keyword is used in descending order, to obtain at least one sorted recommended statement; and sending the at least one sorted recommended statement to the user's device.

[0017] In this method, the number of times the third keyword generates recommended statements is positively correlated with the user's level of interest in the question. The recommended statements are prioritized according to the number of times each third keyword generates recommended statements, from highest to lowest. In other words, recommended statements are displayed to users based on their level of interest in the question. If users see the recommended statements that appear first, it further increases the likelihood of users asking questions based on the recommended statements, thus improving the user experience.

[0018] Optionally, determining at least one recommended statement including the first keyword and the at least one third keyword based on the first keyword and the at least one third keyword includes: determining whether there is a question statement among a plurality of pre-stored question statements that simultaneously includes the first keyword and any third keyword; if there is a question statement among the plurality of pre-stored question statements that simultaneously includes the first keyword and any third keyword, then the question statement that simultaneously includes the first keyword and any third keyword is taken as the at least one recommended statement.

[0019] This method allows at least one recommended statement to be determined from multiple pre-stored question statements, thus reducing the time required to generate recommended statements and improving the efficiency of determining at least one recommended statement.

[0020] Secondly, embodiments of this application provide a data processing apparatus, which includes modules / units / technical means for performing the methods described in the first aspect or any optional implementation of the first aspect.

[0021] For example, the device may include:

[0022] The retrieval module is used to retrieve the question statement;

[0023] A processing module is configured to extract a first keyword and a second keyword from the question statement; wherein the first keyword indicates the business scenario to which the question statement belongs, and the second keyword indicates a specific attribute of the question statement within the business scenario; determine at least one third keyword that has a subordinate relationship with the second keyword based on the inference graph corresponding to the business scenario; wherein the inference graph indicates the subordinate relationship between each attribute and other attributes among multiple attributes in the business scenario; determine at least one target answer statement corresponding to the question statement, and determine at least one recommended statement including the first keyword and the third keyword based on the first keyword and the at least one third keyword; wherein the recommended statement is a question statement composed of the first keyword and the third keyword; and send answer information to the user's device; wherein the answer information includes the at least one target answer statement and the at least one recommended statement.

[0024] Optionally, before determining at least one third keyword that has an affiliated relationship with the second keyword based on the inference graph corresponding to the business scenario, the processing module is further configured to: determine the inference graph corresponding to the business scenario from the multiple candidate inference graphs based on the mapping relationship between the pre-stored set of business scenarios and multiple candidate inference graphs; the set of business scenarios includes the business scenario.

[0025] Optionally, when the processing module determines at least one third keyword that has an affiliated relationship with the second keyword based on the inference graph corresponding to the business scenario, it is specifically used to: determine whether the specified attribute includes at least one sub-attribute based on the inference graph corresponding to the business scenario; if the specified attribute includes at least one sub-attribute, then determine the at least one third keyword based on the at least one sub-attribute.

[0026] Optionally, the processing module is further configured to: if the specified attribute does not include any sub-attribute, determine whether the specified attribute has a parent attribute based on the inference graph corresponding to the business scenario; if the specified attribute has a parent attribute, determine the at least one third keyword based on all attributes other than the specified attribute that are divided by the parent attribute of the specified attribute.

[0027] Optionally, the acquisition module is further configured to: acquire the number of times each third keyword is used to generate recommended statements; when the processing module sends answer information to the user's device, it is specifically configured to: prioritize the at least one recommended statement according to the order of the number of operations of the at least one third keyword from largest to smallest, to obtain at least one sorted recommended statement; and send the at least one sorted recommended statement to the user's device.

[0028] Optionally, when the processing module determines at least one recommended statement including the first keyword and the third keyword based on the first keyword and the at least one third keyword, it is specifically used to: determine whether there is a question statement that simultaneously includes the first keyword and any third keyword among the pre-stored multiple question statements; if there is a question statement that simultaneously includes the first keyword and any third keyword among the pre-stored multiple question statements, then the question statement that simultaneously includes the first keyword and any third keyword is taken as the at least one recommended statement.

[0029] Thirdly, this application provides an electronic device, including: at least one processor; and a memory and a communication interface communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor, by executing the instructions stored in the memory, causes the electronic device to perform the method described in the first aspect or any optional embodiment of the first aspect through the communication interface.

[0030] Fourthly, this application provides a computer-readable storage medium for storing instructions that, when executed, cause the method described in the first aspect or any optional embodiment of the first aspect to be implemented.

[0031] Fifthly, this application provides a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the method described in the first aspect or any optional embodiment of the first aspect.

[0032] The technical effects or advantages of one or more technical solutions provided in the second, third, fourth, and fifth aspects of this application can all be explained by the corresponding technical effects or advantages of one or more technical solutions provided in the first aspect, and will not be repeated here. Attached Figure Description

[0033] Figure 1 A flowchart illustrating a data processing method provided in an embodiment of this application;

[0034] Figure 2 A schematic diagram of a reasoning graph provided in an embodiment of this application;

[0035] Figure 3 A structural diagram of a data processing apparatus provided in an embodiment of this application;

[0036] Figure 4 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0038] The terms "first" and "second" in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the term "comprising" and any variations thereof are intended to cover non-exclusive protection. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. The term "multiple" in this application can mean at least two, for example, two, three, or more, and the embodiments of this application do not impose limitations.

[0039] The term "and / or" in the embodiments of this application is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0040] The data collection, dissemination, and use in this application all comply with relevant national laws and regulations.

[0041] To facilitate understanding of the solutions in the embodiments of this application, the possible application scenarios of the embodiments of this application will be introduced below.

[0042] Intelligent question answering can improve operational efficiency and is widely used in various business processes. However, one-to-one question-and-answer responses are often limited in content and may not meet the user's true needs. Therefore, while answering the question, related questions can be recommended to guide the user to ask further questions and address their real needs. In current technologies, the recommended related questions are often semantically similar to the user's question and may not be relevant. This reduces the likelihood of resolving the user's true needs, resulting in poor intelligence and a poor user experience for intelligent question answering devices.

[0043] Therefore, this application provides a technical solution to improve the intelligence of intelligent question-answering devices and enhance user experience.

[0044] In view of the above scenarios, the data processing method provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0045] See Figure 1 The above is a flowchart illustrating a data processing method provided in this application. This method can be executed by computer devices, such as laptops, desktop computers, and servers, and can also be applied to various devices with computing capabilities, such as intelligent robots in banks. The above devices are merely illustrative examples and are not intended to limit the scope of this application.

[0046] The following example illustrates how this method is executed by a computer device. The method includes:

[0047] S101: Obtain the question statement and extract the first keyword and the second keyword from the question statement.

[0048] The first keyword indicates the business scenario to which the question statement belongs, and the second keyword indicates the specific attribute of the question statement within that business scenario.

[0049] For example, when the question is “What is the definition of financial services business?”, “financial services business” is the primary keyword and “definition” is the secondary keyword; when the question is “What operations can corporate clients perform?”, “corporate clients” is the primary keyword and “operations” is the secondary keyword; when the question is “What are the office hours of Company X?”, “Company X” is the primary keyword and “office hours” is the secondary keyword.

[0050] In one possible implementation, a question statement is input into a trained text recognition model, and the trained text output model outputs the first keyword and the second keyword.

[0051] It is understood that the above is only an example and not a limitation. The first and second keywords can be obtained in other ways, and this application is not limited to this.

[0052] S102: Based on the reasoning graph corresponding to the business scenario, determine at least one third keyword that has an affiliated relationship with the second keyword.

[0053] Among them, the reasoning graph is used to indicate the subordinate relationships between each attribute and other attributes in a business scenario.

[0054] In one possible implementation, the computer device pre-stores a set of business scenarios and the mapping relationship of multiple candidate inference graphs, and determines the inference graph corresponding to the business scenario based on the business scenario indicated by the first keyword; wherein, the set of business scenarios includes at least one business scenario, and the business scenario indicated by the first keyword in this embodiment of the application may be one of the at least one business scenario.

[0055] Understandably, multiple sample question statements can be input into a trained data extraction model to obtain an inference graph, or the inference graph can be configured by relevant business personnel. Furthermore, the inference graphs corresponding to different business scenarios can be the same or different; this application does not impose any restrictions.

[0056] This method allows for the determination of the reasoning graph for a given problem statement when multiple alternative reasoning graphs exist. This is based on the business scenario indicated by the first keyword in the problem statement, thus ensuring the reliability and rationality of the solution.

[0057] The following describes a method for determining at least one third keyword.

[0058] For example, see Figure 2 This is a schematic diagram of a reasoning graph provided in an embodiment of this application. Figure 2 (Only a partial reasoning graph is shown). Apart from the nodes representing business scenarios, the content of each node represents an attribute. The relationships between attributes can be parent-child; for example, if "Operation" is divided into "Regular Operation" and "Special Operation," then "Operation" is the parent attribute of both "Regular Operation" and "Special Operation," and "Regular Operation" and "Special Operation" are the child attributes of "Operation." Alternatively, the relationships can be siblings; for example, if "Operation" is divided into "Regular Operation" and "Special Operation," then "Regular Operation" and "Special Operation" share the same parent attribute and are therefore siblings.

[0059] It is understood that the above is only an example and not a limitation, and subordinate relationships can have other forms of expression, which are not limited in this application.

[0060] In one possible implementation, the system determines whether a specified attribute includes at least one sub-attribute based on the reasoning graph corresponding to the business scenario; if the specified attribute includes at least one sub-attribute, then at least one third keyword is determined based on the at least one sub-attribute.

[0061] For example, the question is "What is the scope of financial services?", where "financial services" is the first keyword and "scope" is the second keyword. The reasoning graph corresponding to the business scenario indicated by the first keyword is as follows: Figure 2As shown, the specified attribute indicated by the second keyword is "range" in the reasoning graph. Based on the reasoning graph, the "range" includes at least one sub-attribute, namely "case", "time", "location" and "comparison". Based on at least one sub-attribute, at least one third keyword is determined to be "case", "time", "location" and "comparison".

[0062] This method allows for the determination of at least one third keyword when a specified attribute includes at least one sub-attribute, meaning the attribute can be further subdivided into more detailed sub-attributes. This third keyword, generated in this way, has a strong correlation with the second keyword and can further refine the second keyword, improving the reliability and completeness of the solution. Furthermore, the subsequent recommended statements generated based on the third keyword can refine the question statements, increasing the likelihood of users asking questions based on the recommended statements, thus enhancing the user experience.

[0063] Optionally, if the specified attribute does not include any sub-attribute, determine whether the specified attribute has a parent attribute based on the reasoning graph corresponding to the business scenario. If the specified attribute has a parent attribute, determine at least one third keyword based on all attributes other than the specified attribute that are divided by the parent attribute of the specified attribute.

[0064] For example, the question is "What employee information is involved in financial services?", where "financial services" is the primary keyword and "employees" is the secondary keyword. The reasoning graph corresponding to the business scenario indicated by the primary keyword is as follows: Figure 2 As shown, the specified attribute indicated by the second keyword is "employee" in the reasoning graph. If any sub-attribute not included in "employee" is determined according to the reasoning graph, then it is determined whether "employee" has a parent attribute. If the parent attribute of "employee" is determined according to the reasoning graph, then "user" is the parent attribute of "employee". The other attributes included by "user" besides "employee" are "customer" and "enterprise". Then at least one third keyword is "customer" and "enterprise".

[0065] Understandably, if the parent property of the specified attribute is only divided into the specified attribute, in other words, the specified attribute does not have a sibling attribute, then it can be determined whether the parent property of the specified attribute has a sibling attribute. If it does, then at least one third keyword is determined based on the sibling attribute of the parent property of the specified attribute.

[0066] This method allows for the determination of at least one third keyword when a specified attribute does not include any sub-attributes, based on other attributes derived from the parent attribute of the specified attribute. This results in a strong correlation between the generated third keyword and the second keyword, improving the reliability and completeness of the solution. Furthermore, the subsequent recommended statements generated based on the third keyword are highly relevant to the question statements, increasing the likelihood of users asking questions based on the recommended statements, thus enhancing the user experience.

[0067] S103: Determine at least one target answer statement corresponding to the question statement, and determine at least one recommended statement including the first keyword and the third keyword based on the first keyword and at least one third keyword.

[0068] The recommended statement is a question statement composed of the first keyword and the third keyword.

[0069] In one possible implementation, multiple candidate answer statements with the same business scenario as the question statement are input into a trained text classification model. The trained text classification model outputs the attribute corresponding to each candidate answer statement. From the multiple candidate answer statements, the candidate answer statement with the same attribute as the specified attribute is determined as at least one answer statement corresponding to the question statement.

[0070] Understandably, the above is merely an example and not a limitation. At least one target answer statement can be obtained in other ways, and this application is not limited to this.

[0071] Optionally, the computer device pre-stores multiple question statements. If there is a question statement among the multiple question statements that includes both the first keyword and any third keyword, then that question statement is used as the recommended statement.

[0072] Understandably, computer devices can also generate at least one recommendation statement in real time based on the first keyword and at least one third keyword. The generation rules for each recommendation statement can be specified according to actual needs. For example, the format of the recommendation statement is "first keyword + third keyword + what is it?". This application does not impose any restrictions.

[0073] This method allows you to determine whether to use pre-stored question statements or regenerate them based on the first and third keywords, thus improving the flexibility of the solution.

[0074] S104: Send the answer information to the user's device.

[0075] The answer information includes at least one target answer statement and at least one recommended statement.

[0076] It is understood that the user's device and the computer device can be the same device or different devices; this application does not impose any restrictions. If the user's device and the computer device are the same device, the answer information will be displayed in the user interface of the computer device.

[0077] In one possible implementation, the number of times each third keyword is used to generate a recommendation statement is obtained, and the recommendation statements are prioritized according to the order of the number of times at least one third keyword is used in descending order, to obtain at least one sorted recommendation statement; the at least one sorted recommendation statement is then sent to the user's device.

[0078] For example, the question is "What employee information is involved in financial services?", where "financial services" is the primary keyword and "employees" is the secondary keyword. The reasoning graph corresponding to the business scenario indicated by the primary keyword is as follows: Figure 2 As shown, at least one third keyword is "customer" and "enterprise". The number of times "customer" and "enterprise" are used to generate recommended statements in the business scenario indicated by the first keyword is 100 times and 50 times, respectively. The recommended statements corresponding to "customer" and "enterprise" are "What is the financial services business that serves customers?" and "What is the financial services business that serves customers?", respectively. The sorted recommended statement is at least "What is the financial services business that serves customers?" and "What is the financial services business that serves customers?".

[0079] In this method, the number of times the third keyword generates recommended statements is positively correlated with the user's level of interest in the question. The recommended statements are prioritized according to the number of times each third keyword generates recommended statements, from highest to lowest. In other words, recommended statements are displayed to users based on their level of interest in the question. If users see the recommended statements that appear first, it further increases the likelihood of users asking questions based on the recommended statements, thus improving the user experience.

[0080] If the user continues to ask questions based on at least one recommended statement, the recommended statement selected by the user will be used as the new question statement, and the above steps S101 to S104 will be executed again. This can guide the user to participate in multiple rounds of dialogue and solve the user's deeper needs.

[0081] In the above schemes S101 to S104, a first keyword indicating the business scenario to which the question statement belongs and a second keyword indicating the specified attribute of the question statement in the business scenario are determined from the question statement. At least one third keyword that has an accessory relationship with the second keyword is determined according to the reasoning graph. At least one recommended statement including the first keyword and the third keyword is determined. In this way, the recommended statement has the same business scenario as the question statement and the correlation between the recommended statement and the question statement is strong, which increases the possibility of users asking questions based on the recommended statement, increases the possibility of solving users' real needs, and improves the intelligence of the intelligent question answering device and the user experience.

[0082] See Figure 3This application provides a data processing apparatus 300, which includes modules / units / technical means for performing the methods executed by computer devices in the above-described method embodiments.

[0083] For example, the device 300 may include:

[0084] Module 301 is used to retrieve the question statement;

[0085] Processing module 302 is configured to extract a first keyword and a second keyword from the question statement; wherein the first keyword indicates the business scenario to which the question statement belongs, and the second keyword indicates a specific attribute of the question statement within the business scenario; determine at least one third keyword that has a subordinate relationship with the second keyword based on the inference graph corresponding to the business scenario; wherein the inference graph indicates the subordinate relationship between each attribute and other attributes among multiple attributes in the business scenario; determine at least one target answer statement corresponding to the question statement, and determine at least one recommended statement including the first keyword and the third keyword based on the first keyword and the at least one third keyword; wherein the recommended statement is a question statement composed of the first keyword and the third keyword; and send answer information to the user's device; wherein the answer information includes the at least one target answer statement and the at least one recommended statement.

[0086] Optionally, before determining at least one third keyword that has an affiliated relationship with the second keyword based on the inference graph corresponding to the business scenario, the processing module 302 is further configured to: determine the inference graph corresponding to the business scenario from the multiple candidate inference graphs based on the mapping relationship between the pre-stored set of business scenarios and multiple candidate inference graphs; the set of business scenarios includes the business scenario.

[0087] Optionally, when the processing module 302 determines at least one third keyword that has an affiliated relationship with the second keyword based on the inference graph corresponding to the business scenario, it is specifically used to: determine whether the specified attribute includes at least one sub-attribute based on the inference graph corresponding to the business scenario; if the specified attribute includes at least one sub-attribute, then determine the at least one third keyword based on the at least one sub-attribute.

[0088] Optionally, the processing module 302 is further configured to: if the specified attribute does not include any sub-attribute, determine whether the specified attribute has a parent attribute based on the inference graph corresponding to the business scenario; if the specified attribute has a parent attribute, determine the at least one third keyword based on all attributes other than the specified attribute that are divided by the parent attribute of the specified attribute.

[0089] Optionally, the acquisition module 301 is further configured to: acquire the number of times each third keyword is used to generate recommended statements; when the processing module 302 sends answer information to the user's device, it is specifically configured to: prioritize the at least one recommended statement according to the order of the number of operations of the at least one third keyword from largest to smallest, to obtain the at least one recommended statement after sorting; and send the at least one recommended statement after sorting to the user's device.

[0090] Optionally, when the processing module 302 determines at least one recommended statement including the first keyword and the third keyword based on the first keyword and the at least one third keyword, it is specifically used to: determine whether there is a question statement that simultaneously includes the first keyword and any third keyword among the pre-stored multiple question statements; if there is a question statement that simultaneously includes the first keyword and any third keyword among the pre-stored multiple question statements, then the question statement that simultaneously includes the first keyword and any third keyword is taken as the at least one recommended statement.

[0091] It should be understood that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0092] As one possible product form of the aforementioned device, see [link to product description]. Figure 4 This application also provides an electronic device 400, comprising:

[0093] At least one processor 401; and a communication interface 403 communicatively connected to the at least one processor 401; the at least one processor 401 causes the electronic device 400 to perform, for example, through the communication interface 403, instructions stored in the memory 402 by executing instructions stored in the memory 402. Figure 1 The method in the illustrated embodiment.

[0094] Optionally, the memory 402 is located outside the electronic device 400.

[0095] Optionally, the electronic device 400 includes the memory 402, which is connected to the at least one processor 401, and stores instructions executable by the at least one processor 401. (Appendix) Figure 4 The dashed line indicates that memory 402 is optional for electronic device 400.

[0096] The processor 401 and the memory 402 can be coupled through an interface circuit or integrated together; no restriction is imposed here.

[0097] This application embodiment does not limit the specific connection medium between the processor 401, memory 402, and communication interface 403. This application embodiment... Figure 4 The processor 401, memory 402, and communication interface 403 are connected via a bus 404. Figure 4 The connections between other components are shown in bold and are for illustrative purposes only, not as limiting information. The bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0098] It should be understood that the processor mentioned in the embodiments of this application can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor, implemented by reading software code stored in memory.

[0099] For example, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0100] It should be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous DRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct RAM (DR RAM).

[0101] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0102] It should be noted that the memories described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0103] As another possible product form, embodiments of this application also provide a computer-readable storage medium for storing instructions that, when executed, cause a computer to perform actions such as... Figure 1 The method in the illustrated embodiment.

[0104] As another possible product form, this application embodiment also provides a computer program product containing instructions, wherein the computer program product stores instructions that, when run on a computer, cause the computer to perform actions such as... Figure 1 The method in the illustrated embodiment.

[0105] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0107] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0108] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes. Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, this application also intends to include such modifications and variations if they fall within the scope of the claims of this application and their equivalents.

Claims

1. A data processing method, characterized by, The method includes: Obtain the question statement, and extract a first keyword and a second keyword from the question statement; wherein, the first keyword is used to indicate the business scenario to which the question statement belongs, and the second keyword is used to indicate the specified attribute of the question statement in the business scenario to which it belongs; Based on the inference graph corresponding to the business scenario, determine whether the specified attribute includes at least one sub-attribute; wherein, the inference graph is used to indicate the subordinate relationship between each attribute and other attributes among multiple attributes in the business scenario; If the specified attribute includes at least one sub-attribute, then at least one third keyword that has a subordinate relationship with the second keyword is determined based on the at least one sub-attribute; or, if the specified attribute does not include any sub-attribute, it is determined whether the specified attribute has a parent attribute based on the reasoning graph; if the specified attribute has a parent attribute, then at least one third keyword that has a subordinate relationship with the second keyword is determined based on all attributes other than the specified attribute that are divided by the parent attribute of the specified attribute. Determine at least one target answer statement corresponding to the question statement, and determine at least one recommended statement including the first keyword and the third keyword based on the first keyword and the at least one third keyword; wherein, the recommended statement is the question statement composed of the first keyword and the third keyword; Send answer information to the user's device; wherein the answer information includes at least one target answer statement and at least one recommended statement.

2. The method as described in claim 1, characterized in that, Before determining whether the specified attribute includes at least one sub-attribute based on the inference graph corresponding to the business scenario, the method further includes: Based on the mapping relationship between a pre-stored set of business scenarios and multiple candidate inference graphs, an inference graph corresponding to the business scenario is determined from the multiple candidate inference graphs; the set of business scenarios includes the business scenario.

3. The method as described in claim 1 or 2, characterized in that, Sending answer information to the user's device includes: Get the number of times each third keyword is used to generate recommended statements; The at least one recommended statement is sorted by priority according to the number of operations of the at least one third keyword in descending order, to obtain the at least one recommended statement after sorting. Send at least one of the sorted recommendation statements to the user's device.

4. The method according to any one of claims 1 to 3, characterized in that, The step of determining at least one recommended statement, including the first keyword and the at least one third keyword, based on the first keyword and the at least one third keyword includes: Determine whether any of the pre-stored multiple question statements contain both the first keyword and any third keyword; If among the pre-stored multiple question statements, there is a question statement that includes both the first keyword and any of the third keywords, then the question statement that includes both the first keyword and any of the third keywords will be used as the at least one recommended statement.

5. A data processing apparatus, characterized in that, The device includes: The retrieval module is used to retrieve the question statement; A processing module is configured to extract a first keyword and a second keyword from the question statement; wherein the first keyword indicates the business scenario to which the question statement belongs, and the second keyword indicates a specified attribute of the question statement within the business scenario; determine whether the specified attribute includes at least one sub-attribute based on the inference graph corresponding to the business scenario; wherein the inference graph indicates the subordinate relationship between each attribute and other attributes among multiple attributes in the business scenario; if the specified attribute includes at least one sub-attribute, determine at least one third keyword that has a subordinate relationship with the second keyword based on the at least one sub-attribute; or, if the specified attribute does not include any sub-attribute, determine whether the specified attribute has a parent attribute based on the inference graph; if the specified attribute has a parent attribute, determine at least one third keyword that has a subordinate relationship with the second keyword based on all attributes other than the specified attribute whose parent attribute is divided by the specified attribute; determine at least one target answer statement corresponding to the question statement, and determine at least one recommended statement including the first keyword and the third keyword based on the first keyword and the at least one third keyword; wherein the recommended statement is a question statement composed of the first keyword and the third keyword. Send answer information to the user's device; wherein the answer information includes at least one target answer statement and at least one recommended statement.

6. The apparatus as claimed in claim 5, characterized in that, Before determining whether the specified attribute includes at least one sub-attribute based on the inference graph corresponding to the business scenario, the processing module is further configured to: Based on the mapping relationship between a pre-stored set of business scenarios and multiple candidate inference graphs, an inference graph corresponding to the business scenario is determined from the multiple candidate inference graphs; the set of business scenarios includes the business scenario.

7. The apparatus as described in claim 5 or 6, characterized in that, When sending answer information to the user's device, the processing module is specifically used for: Get the number of times each third keyword is used to generate recommended statements; The at least one recommended statement is sorted by priority according to the number of operations of the at least one third keyword in descending order, to obtain the at least one recommended statement after sorting. Send at least one of the sorted recommendation statements to the user's device.

8. The apparatus according to any one of claims 5 to 7, characterized in that, When determining at least one recommended statement including the first keyword and the at least one third keyword based on the first keyword and the at least one third keyword, the processing module is specifically used for: Determine whether any of the pre-stored multiple question statements contain both the first keyword and any third keyword; If among the pre-stored multiple question statements, there is a question statement that includes both the first keyword and any of the third keywords, then the question statement that includes both the first keyword and any of the third keywords will be used as the at least one recommended statement.

9. An electronic device, characterized in that, include: At least one processor; And a memory and a communication interface that are communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, by executing the instructions stored in the memory, causes the electronic device to perform the method as described in any one of claims 1 to 4 through the communication interface.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 4.

11. A computer program product, characterized in that, The computer program product includes: computer program code, which, when run on a computer, causes the computer to perform the method as described in any one of claims 1 to 4.

Images