Artificial intelligence-based query processing method and device, computer equipment and medium

Abstract

The invention belongs to the field of artificial intelligence and the field of financial science and technology, and relates to an artificial intelligence-based query processing method, which comprises the following steps of: receiving query information input by a user; performing information analysis on the query information based on the user interaction Agent to obtain a query keyword and a user intention; initial decision information corresponding to the query keyword and the user intention is collected based on the information collection Agent; processing the initial decision information based on an information processing Agent to obtain target decision information; performing standard operation program matching processing on the target decision information based on the retrieval matching Agent to obtain a target standard operation program; based on the decision reply Agent, generating decision reply information according to the target standard operation program; and the decision reply information is sent to the user through the user interaction Agent. The invention further provides a query processing device based on artificial intelligence, computer equipment and a storage medium. According to the method and the device, based on mutual cooperation of the multiple Agents, the accuracy of decision reply to the query information is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology and the field of financial technology, and in particular to artificial intelligence-based query processing methods, devices, computer equipment and storage media. Background Art

[0002] With the rapid development of artificial intelligence technology, intelligent question-answering systems for human-computer interactive dialogues have been widely used in the financial field. For example, they can be used in insurance plan communication, home purchase plan communication, and so on.

[0003] At present, the intelligent question-answering systems used by financial enterprises, such as insurance enterprises, are usually intelligent question-answering systems of task-based robots based on scripts. However, task-based robots based on scripts are often suitable for handling simple task communication scenarios. For complex task communication scenarios corresponding to more complex query information input by users, task-based robots based on scripts are usually unable to accurately and effectively complete the decision-making response processing of complex task communication scenarios, resulting in low accuracy of decision-making responses to query information. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a query processing method, device, computer equipment and storage medium based on artificial intelligence to solve the technical problem in the prior art that, for complex task communication scenarios corresponding to more complex query information input by users, script-based task robots are usually unable to accurately and effectively complete the decision-making response processing of complex task communication scenarios, resulting in low accuracy of decision-making responses to query information.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a query processing method based on artificial intelligence, which adopts the following technical solution:

[0006] Receive query information input by the user;

[0007] The query information is analyzed based on a preset user interaction agent to obtain query keywords and user intentions corresponding to the query information;

[0008] Collecting initial decision information corresponding to the query keyword and the user intention based on a preset information collection agent;

[0009] Processing the initial decision information based on a preset information processing agent to obtain corresponding target decision information;

[0010] Based on a preset retrieval matching Agent, the target decision information is matched with a standard operating procedure to obtain a target standard operating procedure corresponding to the target decision information;

[0011] Based on a preset decision reply Agent, generating decision reply information corresponding to the query information according to the target standard operating procedure;

[0012] The decision reply information is sent to the user through the user interaction Agent.

[0013] Furthermore, the step of collecting the initial decision information corresponding to the query keyword and the user intention based on the preset information collection Agent specifically includes:

[0014] Calling the information collection Agent;

[0015] Constructing query conditions corresponding to the query keywords and the user intention through the information collection agent;

[0016] Determine the query data source and retrieval strategy corresponding to the query condition;

[0017] Based on the retrieval strategy, the query data source is searched using the query condition to obtain retrieval information corresponding to the query condition;

[0018] The initial decision information is generated based on the search information.

[0019] Furthermore, the step of processing the initial decision information based on the preset information processing Agent to obtain the corresponding target decision information specifically includes:

[0020] Calling the information processing Agent;

[0021] Based on the information processing Agent, data cleaning is performed on the initial decision information to obtain corresponding first decision information;

[0022] Performing format conversion processing on the first decision information to obtain corresponding second decision information;

[0023] performing feature extraction processing on the second decision information to obtain corresponding third decision information;

[0024] The third decision information is used as the target decision information.

[0025] Furthermore, the step of performing standard operating procedure matching processing on the target decision information based on the preset retrieval matching Agent to obtain the target standard operating procedure corresponding to the target decision information specifically includes:

[0026] Calling the retrieval matching Agent;

[0027] Based on the retrieval matching Agent, a preset similarity algorithm is used to calculate the similarity between the target decision information and all preset standard operating procedures;

[0028] Filter out a first standard operating procedure having a similarity greater than a preset similarity threshold from all the standard operating procedures;

[0029] Determining whether the number of the first standard operating procedures is greater than 1;

[0030] If so, generating a comprehensive evaluation score for each of the first standard operating procedures based on the priority, feedback effect, and execution efficiency of each of the first standard operating procedures;

[0031] Selecting the second standard operating procedure with the highest comprehensive evaluation score from all the first standard operating procedures;

[0032] The second standard operating procedure is used as the target standard operating procedure.

[0033] Furthermore, the step of generating a comprehensive evaluation score of each of the first standard operating procedures based on the priority, feedback effect, and execution efficiency of each of the first standard operating procedures specifically includes:

[0034] Obtaining a specified priority, a specified feedback effect, and a specified execution efficiency of a specified standard operating procedure; wherein the specified standard operating procedure is any one of all the first standard operating procedures;

[0035] generating a designated priority value corresponding to the designated priority based on a preset priority mapping table, and generating a designated feedback effect value corresponding to the designated feedback effect based on a preset effect mapping table;

[0036] Determine the target weight selection algorithm;

[0037] Generate a first weight, a second weight, and a third weight corresponding to the priority, the feedback effect, and the execution efficiency, respectively, based on the target weight selection algorithm;

[0038] Calculate the specified priority value, the specified feedback effect value, the specified execution efficiency, the first weight, the second weight, and the third weight based on a preset evaluation calculation formula to obtain a corresponding calculation score;

[0039] The calculated score is used as the comprehensive evaluation score of the designated standard operating procedure.

[0040] Furthermore, the step of generating decision reply information corresponding to the query information based on the preset decision reply Agent according to the target standard operating procedure specifically includes:

[0041] Calling the decision reply Agent;

[0042] Determine the target information type;

[0043] Based on the decision reply Agent, filtering content information corresponding to the target information type from the target standard operating procedure;

[0044] Convert the content information based on a preset format to obtain corresponding target content information;

[0045] The decision reply information is generated based on the target content information.

[0046] Furthermore, the step of generating the decision reply information based on the target content information specifically includes:

[0047] Performing grammar checking on the target content information;

[0048] If the target content information passes the syntax check, then a semantic check is performed on the target content;

[0049] If the target content information passes the semantic check, then performing a logical check on the target content;

[0050] If the target content information passes the logic check, the target content information is used as the decision reply information.

[0051] In order to solve the above technical problems, the embodiment of the present application further provides a query processing device based on artificial intelligence, which adopts the following technical solution:

[0052] A receiving module, used for receiving query information input by a user;

[0053] A parsing module, used to parse the query information based on a preset user interaction agent to obtain query keywords and user intentions corresponding to the query information;

[0054] A collection module, used to collect initial decision information corresponding to the query keyword and the user intention based on a preset information collection agent;

[0055] A processing module, used to process the initial decision information based on a preset information processing Agent to obtain corresponding target decision information;

[0056] A matching module, used for performing standard operating procedure matching processing on the target decision information based on a preset retrieval matching Agent to obtain a target standard operating procedure corresponding to the target decision information;

[0057] A generating module, configured to generate decision reply information corresponding to the query information based on a preset decision reply Agent and according to the target standard operating procedure;

[0058] The sending module is used to send the decision reply information to the user through the user interaction Agent.

[0059] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0060] Receive query information input by the user;

[0061] The query information is analyzed based on a preset user interaction agent to obtain query keywords and user intentions corresponding to the query information;

[0062] Collecting initial decision information corresponding to the query keyword and the user intention based on a preset information collection agent;

[0063] Processing the initial decision information based on a preset information processing agent to obtain corresponding target decision information;

[0064] Based on a preset retrieval matching Agent, the target decision information is matched with a standard operating procedure to obtain a target standard operating procedure corresponding to the target decision information;

[0065] Based on a preset decision reply Agent, generating decision reply information corresponding to the query information according to the target standard operating procedure;

[0066] The decision reply information is sent to the user through the user interaction Agent.

[0067] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0068] Receive query information input by the user;

[0069] The query information is analyzed based on a preset user interaction agent to obtain query keywords and user intentions corresponding to the query information;

[0070] Collecting initial decision information corresponding to the query keyword and the user intention based on a preset information collection agent;

[0071] Processing the initial decision information based on a preset information processing agent to obtain corresponding target decision information;

[0072] Based on a preset retrieval matching Agent, the target decision information is matched with a standard operating procedure to obtain a target standard operating procedure corresponding to the target decision information;

[0073] Based on a preset decision reply Agent, generating decision reply information corresponding to the query information according to the target standard operating procedure;

[0074] The decision reply information is sent to the user through the user interaction Agent.

[0075] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0076] The present application first receives the query information input by the user; then, based on the preset user interaction agent, the query information is analyzed to obtain the query keywords and user intentions corresponding to the query information; then, based on the preset information collection agent, the initial decision information corresponding to the query keywords and the user intentions is collected; subsequently, based on the preset information processing agent, the initial decision information is processed to obtain the corresponding target decision information; further, based on the preset retrieval matching agent, the target decision information is matched with the standard operating procedure to obtain the target standard operating procedure corresponding to the target decision information; and based on the preset decision reply agent, the decision reply information corresponding to the query information is generated according to the target standard operating procedure; finally, the decision reply information is sent to the user through the user interaction agent. The present application performs decision reply processing on the query information input by the user based on the mutual cooperation of the user interaction agent, the information collection agent, the information processing agent, the retrieval matching agent and the decision reply agent, so as to realize the rapid output of accurate decision reply information for the query information input by the user, and effectively improve the accuracy of the decision reply to the query information. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0078] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0079] Figure 2 A flowchart of an embodiment of an artificial intelligence-based query processing method according to the present application;

[0080] Figure 3 is a structural schematic diagram of an embodiment of an artificial intelligence-based query processing device according to the present application;

[0081] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0082] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0083] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0084] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0085] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0086] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0087] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and the like.

[0088] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0089] It should be noted that the artificial intelligence-based query processing method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based query processing device is generally arranged in the server / terminal device.

[0090] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0091] Continue to refer Figure 2 , showing a flow chart of an embodiment of an artificial intelligence-based query processing method according to the present application. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted. The artificial intelligence-based query processing method provided in the embodiment of the present application can be applied to any scenario where query processing is required, and the artificial intelligence-based query processing method can be applied to products in these scenarios, for example, query information reply processing of an intelligent question and answer system in the field of finance and insurance. The artificial intelligence-based query processing method comprises the following steps:

[0092] Step S201, receiving query information input by a user.

[0093] In this embodiment, the query processing method based on artificial intelligence is executed on the electronic device (e.g. Figure 1The server / terminal device shown in the figure) can obtain the query information input by the user through a wired connection or a wireless connection. It should be pointed out that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (Ultra Wi DeBand) connection, and other wireless connection methods currently known or to be developed in the future. The execution subject of this application is specifically a query processing robot system based on the Multi-Agent framework. The Multi-Agent System (MAS) is a collection of multiple Agents, and its multiple Agent members coordinate and serve each other to complete a task together. Its goal is to build a large and complex system into a small, mutually communicating and coordinated, and easy-to-manage system. Specifically, the above-mentioned query processing robot system is a pre-built robot system for making decisions and responses to user queries during the dialogue process. The system is at least a complex system including a user interaction agent, an information collection agent, an information processing agent, a retrieval matching agent, and a decision response agent. The communication between the agents can be achieved through a message passing mechanism, such as TCP / IP-based socket communication, HTTP request / response mechanism or a dedicated agent communication protocol. The agents share information, exchange opinions and coordinate actions to ensure the smooth completion of the decision-making response task. Among them, the above-mentioned query information can be a query information with high complexity input by the user during the dialogue with the query processing robot system. The query information can be a query question in any format. For example, in the business scenario of insurance product consultation in the financial insurance field, the query information may include information on consulting insurance costs, insurance terms confirmation information, information requesting the recommendation of suitable insurance products, and so on. In addition, high complexity can refer to a large number of words in the query information.

[0094] Step S202: parsing the query information based on a preset user interaction Agent to obtain query keywords and user intentions corresponding to the query information.

[0095] In this embodiment, the user interaction agent is an intelligent agent built based on natural language processing technology. After receiving the query information input by the user, the user interaction agent will perform lexical analysis, syntactic analysis and semantic understanding processing on the query information according to the natural language processing technology, and output the query keywords corresponding to the query information and the user intention.

[0096] Step S203: collecting initial decision information corresponding to the query keyword and the user intention based on a preset information collection Agent.

[0097] In this embodiment, the specific implementation process of the preset information collection Agent collecting the initial decision information corresponding to the query keyword and the user intention will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated here.

[0098] Step S204: Process the initial decision information based on a preset information processing Agent to obtain corresponding target decision information.

[0099] In this embodiment, the above-mentioned specific implementation process of processing the initial decision information based on the preset information processing Agent to obtain the corresponding target decision information will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated here.

[0100] Step S205: performing standard operating procedure matching processing on the target decision information based on a preset retrieval matching Agent to obtain a target standard operating procedure corresponding to the target decision information.

[0101] In this embodiment, the above-mentioned preset retrieval matching Agent performs standard operating procedure matching processing on the target decision information to obtain the specific implementation process of the target standard operating procedure corresponding to the target decision information. This application will provide further detailed descriptions of this in subsequent specific embodiments and will not be elaborated on here.

[0102] Step S206: Based on the preset decision reply Agent, decision reply information corresponding to the query information is generated according to the target standard operating procedure.

[0103] In this embodiment, the above-mentioned specific implementation process of the preset decision response Agent generating decision response information corresponding to the query information according to the target standard operating procedure will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0104] Step S207: sending the decision reply information to the user through the user interaction Agent.

[0105] In this embodiment, after the decision reply agent generates decision reply information corresponding to the query information, it will interact with the above-mentioned user interaction agent through a message passing mechanism, that is, transmit the above-mentioned decision reply information to the user interaction agent, so that the decision reply information can be subsequently sent to the user through the user interaction agent to complete the feedback processing of the query information input by the user.

[0106] The present application performs decision-making response processing on the query information input by the user through the mutual collaboration of the user interaction agent, the information collection agent, the information processing agent, the retrieval matching agent and the decision response agent, so as to quickly output accurate decision response information for the query information input by the user, and effectively improve the accuracy of the decision response to the query information.

[0107] In some optional implementations, step S203 includes the following steps:

[0108] Call the information collection Agent.

[0109] In this embodiment, the above-mentioned information collection agent is a pre-built intelligent entity that is used to retrieve data or information directly related to the query keywords and user intentions corresponding to the query information input by the user from various data sources, which can help the system understand the user's intentions and respond accordingly.

[0110] The information collection agent constructs query conditions corresponding to the query keywords and the user intention.

[0111] In this embodiment, the query conditions may include specific data fields that match the query keywords and the user intent, for example, may include at least keyword matching, time range, geographic location, etc.

[0112] Determine the query data source and retrieval strategy corresponding to the query condition.

[0113] In this embodiment, the query data source may include at least internal databases, external servers, file systems, search engines, etc. The search strategy may include a strategy of using the query conditions to search all query data sources separately, thus ensuring the comprehensiveness and accuracy of the search.

[0114] Based on the retrieval strategy, the query data source is searched using the query condition to obtain retrieval information corresponding to the query condition.

[0115] In this embodiment, the information format of the search information corresponding to the query condition obtained by querying the data source may be structured information, such as records in an internal database, or may be unstructured information, such as web page content.

[0116] The initial decision information is generated based on the search information.

[0117] In this embodiment, the query data source includes multiple data. The integrated data is obtained by integrating the search information obtained from each query data source, and then the integrated data is used as the initial decision information.

[0118] This application calls the information collection agent; then constructs the query conditions corresponding to the query keywords and the user intention through the information collection agent; then determines the query data source and retrieval strategy corresponding to the query conditions; subsequently, based on the retrieval strategy, uses the query conditions to perform retrieval processing on the query data source to obtain retrieval information corresponding to the query conditions; and further generates the initial decision information based on the retrieval information. This application can quickly construct a retrieval strategy corresponding to the query keywords and the user intention through the use of the information collection agent, and then use the retrieval strategy corresponding to the query conditions to perform retrieval processing on the query data source, so as to quickly and accurately generate the initial decision information related to the query information input by the user, thereby improving the generation efficiency and generation accuracy of the initial decision information.

[0119] In some optional implementations of this embodiment, step S204 includes the following steps:

[0120] Call the information processing Agent.

[0121] In this embodiment, the information processing Agent is a pre-built intelligent entity used to process and organize the original decision information collected by the information collection Agent so as to perform subsequent processing and decision-making.

[0122] Based on the information processing Agent, data cleaning is performed on the initial decision information to obtain corresponding first decision information.

[0123] In this embodiment, the data cleaning process at least includes removing noise, filling missing values, processing abnormal values, etc. By performing data cleaning on the initial decision information, the data accuracy of the obtained first decision information can be guaranteed.

[0124] The first decision information is format converted to obtain corresponding second decision information.

[0125] In this embodiment, the above-mentioned format conversion processing refers to the processing of converting the first decision information into a processing format that conforms to the above-mentioned retrieval matching agent and decision reply agent, that is, the subsequent retrieval matching agent and decision reply agent can smoothly use the first decision information in the process of retrieval matching and decision reply.

[0126] Perform feature extraction processing on the second decision information to obtain corresponding third decision information.

[0127] In this embodiment, the feature extraction process refers to the process of extracting key features from the second decision information, so that a more accurate decision response process can be performed by subsequently performing decision processing on the obtained third decision information. In addition, since only the third decision information that has undergone key feature extraction needs to be processed later, without the need to process all the second decision information, the workload of the decision response processing for the query information can be effectively reduced, thereby improving the processing efficiency of the decision response processing. Among them, any one of the key feature extraction algorithms such as principal component analysis, local linear embedding, linear discriminant analysis, sparse coding method of unsupervised learning, and decision tree can be used to implement feature extraction processing for the second decision information.

[0128] The third decision information is used as the target decision information.

[0129] The present application calls the information processing Agent; then based on the information processing Agent, the initial decision information is cleaned and processed to obtain the corresponding first decision information; then the first decision information is converted into a format to obtain the corresponding second decision information; the second decision information is subsequently subjected to feature extraction to obtain the corresponding third decision information, and the third decision information is used as the target decision information. The present application calls the information processing Agent to perform data cleaning, format conversion, and feature extraction on the initial decision information, so as to quickly complete the processing of the initial decision information and obtain the target decision information that meets the format requirements and is accurate, thereby ensuring the data accuracy of the obtained target decision information.

[0130] In some optional implementations, step S205 includes the following steps:

[0131] Call the retrieval matching Agent.

[0132] In this embodiment, the retrieval and matching Agent is a pre-built intelligent agent that retrieves and matches the most suitable standard operating procedures based on the target decision information processed by the information processing Agent, and provides a basis for decision-making responses.

[0133] Based on the retrieval matching Agent, a preset similarity algorithm is used to calculate the similarity between the target decision information and all preset standard operating procedures.

[0134] In this embodiment, a set of SOPs (Standard Operating Procedures) for handling specific types of problems or scenarios is pre-built, and the SOP set includes a certain number of standard operating procedures. There is no specific limitation on the selection of the similarity algorithm, for example, any one of Euclidean similarity, cosine similarity, Gerard similarity, and Pearson correlation coefficient can be selected as the similarity algorithm.

[0135] A first standard operating procedure having a similarity greater than a preset similarity threshold is screened out from all the standard operating procedures.

[0136] In this embodiment, there is no specific limitation on the value of the similarity threshold, which can be determined according to actual similarity matching requirements, for example, it can be set to 0.88.

[0137] Determine whether the number of the first standard operating procedures is greater than 1.

[0138] In this embodiment, the number of the first standard operating procedures may be 1, or greater than 1. If the number of the first standard operating procedures is equal to 1, the first standard operating procedure is directly used as the target standard operating procedure.

[0139] If so, a comprehensive evaluation score of each of the first standard operating procedures is generated based on the priority, feedback effect, and execution efficiency of each of the first standard operating procedures.

[0140] In this embodiment, different priorities are assigned to the standard operating procedures in advance according to their importance and urgency. The priorities of the standard operating procedures can be divided into three levels: high priority, medium priority, and low priority. Among them, during the historical use of the standard operating procedures, the feedback of users on the use effects of various standard operating procedures will also be recorded. The feedback effect can be divided into excellent effect, good effect, qualified effect, and unqualified effect. In addition, during the historical use of the standard operating procedures, the execution efficiency of various standard operating procedures during use will also be recorded. The execution efficiency of the standard operating procedure refers to the quotient of the total duration and the total number of times corresponding to the generation of decision reply information according to the standard operating procedure within a preset time period. There is no specific limitation on the selection of the preset time period, for example, it can be the most recent year. In addition, the specific implementation process of generating the comprehensive evaluation score of each of the first standard operating procedures based on the priority, feedback effect and execution efficiency of each of the first standard operating procedures will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0141] The second standard operating procedure with the highest comprehensive evaluation score is selected from all the first standard operating procedures.

[0142] In this embodiment, the comprehensive evaluation scores of the first standard operating procedures may be numerically compared to select the second standard operating procedure with the highest comprehensive evaluation score from all the first standard operating procedures.

[0143] The second standard operating procedure is used as the target standard operating procedure.

[0144] The present application calls the retrieval matching agent, and based on the retrieval matching agent, uses a preset similarity algorithm to calculate the similarity between the target decision information and all preset standard operating procedures; then selects the first standard operating procedure whose similarity is greater than the preset similarity threshold from all the standard operating procedures; then determines whether the number of the first standard operating procedures is greater than 1; if so, generates a comprehensive evaluation score for each of the first standard operating procedures based on the priority, feedback effect and execution efficiency of each of the first standard operating procedures; subsequently selects the second standard operating procedure with the highest comprehensive evaluation score from all of the first standard operating procedures, and uses the second standard operating procedure as the target standard operating procedure. The present application uses the retrieval matching agent, and when the number of the first standard operating procedures matching the target decision information output by the information processing agent is greater than 1 according to the similarity algorithm, it will intelligently generate a comprehensive evaluation score for each of the first standard operating procedures based on the priority, feedback effect and execution efficiency of each of the first standard operating procedures, and further uses the second standard operating procedure with the highest comprehensive evaluation score as the target standard operating procedure. By using the second standard operating procedure with the best processing evaluation corresponding to the priority, feedback effect and execution efficiency as the final target standard operating procedure, the accuracy of the obtained target standard operating procedure is guaranteed. And subsequently, by using the decision reply Agent to generate decision reply information corresponding to the query information according to the target standard operating procedure, the accuracy of the generated decision reply information can be effectively improved, and the generation efficiency of the decision reply information can be improved.

[0145] In some optional implementations, generating a comprehensive evaluation score of each of the first standard operating procedures based on the priority, feedback effect, and execution efficiency of each of the first standard operating procedures includes the following steps:

[0146] Get the specified priority, specified feedback effect, and specified execution efficiency of the specified standard operating procedure.

[0147] In this embodiment, the designated standard operating procedure is any one of all the first standard operating procedures.

[0148] A designated priority value corresponding to the designated priority is generated based on a preset priority mapping table, and a designated feedback effect value corresponding to the designated feedback effect is generated based on a preset effect mapping table.

[0149] In this embodiment, the above-mentioned priority mapping table is a data table pre-constructed according to actual business usage requirements, storing multiple priorities and mapping values ​​corresponding to each priority. Specifically, the priorities include high priority, medium priority and low priority. Correspondingly, the mapping value corresponding to the high priority is 3, the mapping value corresponding to the medium priority is 2, and the mapping value corresponding to the low priority is 1. In addition, the above-mentioned effect mapping table is a data table pre-constructed according to actual business usage requirements, storing multiple effects and mapping values ​​corresponding to each effect. Specifically, the effects include excellent effect, good effect, qualified effect, and unqualified effect. Correspondingly, the mapping value corresponding to the excellent effect is 4, the mapping value corresponding to the good effect is 3, the mapping value corresponding to the qualified effect is 2, and the mapping value corresponding to the unqualified effect is 1.

[0150] Determine the target weight selection algorithm.

[0151] In this embodiment, the weight determination algorithm may include random selection from a hierarchy analysis method, a principal component analysis method, a factor analysis method, an entropy method, and a standardization method.

[0152] Based on the target weight selection algorithm, a first weight, a second weight and a third weight corresponding to the priority, the feedback effect and the execution efficiency are generated respectively.

[0153] In this embodiment, the priority, feedback effect and execution efficiency can be weighted according to the operation steps of calculating weights matched by the target weight selection algorithm, thereby generating a first weight, a second weight and a third weight corresponding to the priority, feedback effect and execution efficiency respectively.

[0154] Calculate the specified priority value, the specified feedback effect value, the specified execution efficiency, the first weight, the second weight, and the third weight based on a preset evaluation calculation formula to obtain a corresponding calculation score;

[0155] In this embodiment, the evaluation calculation formula may specifically include: S=a*U+b*V+c / W, where U is the specified priority value, a is the first weight, V is the specified feedback effect value, b is the second weight, W is the specified execution efficiency, and c is the third weight. The specified priority value, the specified feedback effect value, the specified execution efficiency, the first weight, the second weight, and the third weight may be substituted into the corresponding positions in the evaluation calculation formula to perform calculation, thereby obtaining the corresponding calculation score.

[0156] The calculated score is used as the comprehensive evaluation score of the designated standard operating procedure.

[0157] The present application generates a designated priority value corresponding to the designated priority and a designated feedback effect value corresponding to the designated feedback effect based on the use of a priority mapping table and an effect mapping table, and then generates a first weight, a second weight and a third weight corresponding to the priority, the feedback effect and the execution efficiency respectively based on a target weight selection algorithm, and then calculates and processes the designated priority value, the designated feedback effect value, the designated execution efficiency, the first weight, the second weight and the third weight based on the use of an evaluation calculation formula, so as to realize fast and accurate generation of a comprehensive evaluation score for a designated standard operating procedure, improve the efficiency of generating a comprehensive evaluation score for a designated standard operating procedure, and ensure the accuracy of the obtained designated standard operating procedure.

[0158] In some optional implementations of this embodiment, step S206 includes the following steps:

[0159] Call the decision reply Agent.

[0160] In this embodiment, the decision response agent is a pre-built intelligent agent used to generate corresponding decision responses according to the matching standard operating procedures.

[0161] Determine the target information type.

[0162] In this embodiment, the above-mentioned target information type refers to the type corresponding to the key information in the target standard operating procedure, which may specifically include the operation step type, precaution type, personnel configuration type, etc.

[0163] Based on the decision reply Agent, content information corresponding to the target information type is filtered out from the target standard operating procedure.

[0164] In this embodiment, the target standard operating procedure is screened by using the target information type to obtain corresponding content information, which may include at least operation steps, precautions, and personnel configuration.

[0165] The content information is converted based on a preset format to obtain corresponding target content information.

[0166] In this embodiment, the preset format is a human-readable format.

[0167] The decision reply information is generated based on the target content information.

[0168] In this embodiment, the specific implementation process of generating the decision reply information based on the target content information will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0169] This application calls the decision reply agent; then determines the target information type, and based on the decision reply agent, screens out content information corresponding to the target information type from the target standard operating procedure; then converts and processes the content information based on a preset format to obtain the corresponding target content information; and subsequently generates the decision reply information based on the target content information. This application is based on the use of the decision reply agent, and generates decision reply information corresponding to the query information according to the target standard operating procedure. Since the target standard operating procedure is the standard operating procedure with the best processing evaluation corresponding to priority, feedback effect and execution efficiency among all standard operating procedures, the use of the target standard operating procedure to generate decision reply information corresponding to the query information can effectively improve the accuracy of the generated decision reply information.

[0170] In some optional implementations of this embodiment, generating the decision reply information based on the target content information includes the following steps:

[0171] Performing syntax check on the target content information.

[0172] In this embodiment, a grammar analyzer may be called to check whether the target content information complies with grammar rules. The grammar rules may at least include subject-verb-object structure, sentence component integrity and other rules.

[0173] If the target content information passes the syntax check, a semantic check is performed on the target content.

[0174] In this embodiment, the semantic verification refers to a verification that determines whether the target content information has logical coherence and consistency by analyzing the semantic relationship between words or phrases in the target content information.

[0175] If the target content information passes the semantic check, a logical check is performed on the target content.

[0176] In this embodiment, the above-mentioned logic verification refers to the verification processing of logical structure analysis, context consistency check and fact verification of the target content information. Among them, the above-mentioned logical structure analysis refers to the analysis of the logical structure of the target content information, such as cause and effect relationship, conditional relationship, etc., to ensure that the target content information is logically coherent and reasonable. The above-mentioned context consistency check refers to checking whether there are any inconsistencies or contradictions with the context in the target content information, so as to ensure that the target content information is consistent with the user's query and context information. The above-mentioned fact verification refers to the use of external data sources or knowledge bases to fact-check the factual information contained in the target content information to ensure accuracy.

[0177] If the target content information passes the logic check, the target content information is used as the decision reply information.

[0178] In this embodiment, only if the target content information passes the syntax check, semantic check and logic check, the target content information is determined to be accurate and complete and meets the user's query intent, and serves as the final decision reply information.

[0179] This application performs a syntax check on the target content information; if the target content information passes the syntax check, a semantic check is performed on the target content; if the target content information passes the semantic check, a logic check is performed on the target content; if the target content information passes the logic check, the target content information is used as the decision response information. After obtaining the target content information, this application will further verify the target content information. Only after detecting that the target content information has passed the syntax check, semantic check, and logic check, will the target content information be used as the final decision response information, thereby ensuring that the target content information obtained is accurate, complete, and meets the user's query intent, thereby ensuring the accuracy of the target content information.

[0180] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0181] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned decision response information, the above-mentioned decision response information can also be stored in a node of a blockchain.

[0182] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0183] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0184] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0185] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0186] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0187] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a query processing device based on artificial intelligence, and the embodiment of the device is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0188] like Figure 3 As shown, the artificial intelligence-based query processing device 300 described in this embodiment includes: a receiving module 301, a parsing module 302, a collecting module 303, a processing module 304, a matching module 305, a generating module 306 and a sending module 307. Among them:

[0189] The receiving module 301 is used to receive query information input by the user;

[0190] The parsing module 302 is used to parse the query information based on a preset user interaction agent to obtain query keywords and user intentions corresponding to the query information;

[0191] A collection module 303 is used to collect initial decision information corresponding to the query keyword and the user intention based on a preset information collection agent;

[0192] A processing module 304 is used to process the initial decision information based on a preset information processing agent to obtain corresponding target decision information;

[0193] A matching module 305 is used to perform standard operating procedure matching processing on the target decision information based on a preset search matching Agent to obtain a target standard operating procedure corresponding to the target decision information;

[0194] A generating module 306, configured to generate decision reply information corresponding to the query information according to the target standard operating procedure based on a preset decision reply Agent;

[0195] The sending module 307 is used to send the decision reply information to the user through the user interaction Agent.

[0196] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based query processing method in the aforementioned implementation mode, and are not described in detail here.

[0197] In some optional implementations of this embodiment, the collection module 303 includes:

[0198] A first calling submodule is used to call the information collection Agent;

[0199] A construction submodule, used to construct a query condition corresponding to the query keyword and the user intention through the information collection agent;

[0200] A first determination submodule is used to determine a query data source and a retrieval strategy corresponding to the query condition;

[0201] A retrieval submodule, configured to perform retrieval processing on the query data source using the query condition based on the retrieval strategy to obtain retrieval information corresponding to the query condition;

[0202] The first generating submodule is used to generate the initial decision information based on the search information.

[0203] In some optional implementations of this embodiment, the processing module 304 includes:

[0204] The second calling submodule is used to call the information processing Agent;

[0205] A cleaning submodule, configured to perform data cleaning processing on the initial decision information based on the information processing Agent to obtain corresponding first decision information;

[0206] A first conversion submodule, used for performing format conversion processing on the first decision information to obtain corresponding second decision information;

[0207] an extraction submodule, configured to perform feature extraction processing on the second decision information to obtain corresponding third decision information;

[0208] The second determining submodule is used to use the third decision information as the target decision information.

[0209] In some optional implementations of this embodiment, the matching module 305 includes:

[0210] The third calling submodule is used to call the search and matching Agent;

[0211] A calculation submodule, used for calculating the similarity between the target decision information and all preset standard operating procedures using a preset similarity algorithm based on the retrieval matching Agent;

[0212] A first screening submodule, used to screen out a first standard operating procedure having a similarity greater than a preset similarity threshold from all the standard operating procedures;

[0213] A judging submodule, used for judging whether the number of the first standard operating procedures is greater than 1;

[0214] A second generating submodule, for generating a comprehensive evaluation score of each of the first standard operating procedures based on the priority, feedback effect and execution efficiency of each of the first standard operating procedures;

[0215] A second screening submodule, used to screen out a second standard operating procedure with the highest comprehensive evaluation score from all the first standard operating procedures;

[0216] The third determining submodule is configured to use the second standard operating procedure as the target standard operating procedure.

[0217] In some optional implementations of this embodiment, the second generating submodule includes:

[0218] An acquisition unit, used to acquire a specified priority, a specified feedback effect, and a specified execution efficiency of a specified standard operating procedure; wherein the specified standard operating procedure is any one of all the first standard operating procedures;

[0219] A first generating unit, configured to generate a designated priority value corresponding to the designated priority based on a preset priority mapping table, and to generate a designated feedback effect value corresponding to the designated feedback effect based on a preset effect mapping table;

[0220] A first determining unit, used to determine a target weight selection algorithm;

[0221] A second generating unit, configured to generate, based on the target weight selection algorithm, a first weight, a second weight, and a third weight corresponding to the priority, the feedback effect, and the execution efficiency, respectively;

[0222] a calculation unit, configured to calculate the specified priority value, the specified feedback effect value, the specified execution efficiency, the first weight, the second weight, and the third weight based on a preset evaluation calculation formula to obtain a corresponding calculation score;

[0223] The second determining unit is configured to use the calculated score as a comprehensive evaluation score of the designated standard operating procedure.

[0224] In some optional implementations of this embodiment, the generating module 306 includes:

[0225] The fourth calling submodule is used to call the decision reply Agent;

[0226] The fourth determination submodule is used to determine the target information type;

[0227] A third screening submodule, configured to screen content information corresponding to the target information type from the target standard operating procedure based on the decision reply Agent;

[0228] A second conversion submodule, configured to convert the content information based on a preset format to obtain corresponding target content information;

[0229] The third generating submodule is used to generate the decision reply information based on the target content information.

[0230] In some optional implementations of this embodiment, the third generation submodule includes:

[0231] A first verification unit, configured to perform syntax verification on the target content information;

[0232] A second verification unit, configured to perform semantic verification on the target content if the target content information passes the grammatical verification;

[0233] A third verification unit, configured to perform a logic verification on the target content if the target content information passes the semantic verification;

[0234] The third determining unit is configured to use the target content information as the decision reply information if the target content information passes the logic check.

[0235] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0236] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0237] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0238] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the query processing method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0239] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the computer-readable instructions stored in the memory 41 or process data, such as running the computer-readable instructions of the artificial intelligence-based query processing method.

[0240] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0241] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based query processing method.

[0242] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0243] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A query processing method based on artificial intelligence, characterized in that: The steps include: Receive query information input by the user; The query information is analyzed based on a preset user interaction agent to obtain query keywords and user intentions corresponding to the query information; Collecting initial decision information corresponding to the query keyword and the user intention based on a preset information collection agent; Processing the initial decision information based on a preset information processing agent to obtain corresponding target decision information; Based on a preset retrieval matching Agent, the target decision information is matched with a standard operating procedure to obtain a target standard operating procedure corresponding to the target decision information; Based on a preset decision reply Agent, generating decision reply information corresponding to the query information according to the target standard operating procedure; The decision reply information is sent to the user through the user interaction Agent.

2. The query processing method based on artificial intelligence according to claim 1, characterized in that: The step of collecting the initial decision information corresponding to the query keyword and the user intention based on the preset information collection Agent specifically includes: Calling the information collection Agent; Constructing query conditions corresponding to the query keywords and the user intention through the information collection agent; Determine the query data source and retrieval strategy corresponding to the query condition; Based on the retrieval strategy, the query data source is searched using the query condition to obtain retrieval information corresponding to the query condition; The initial decision information is generated based on the search information.

3. The query processing method based on artificial intelligence according to claim 1, characterized in that: The step of processing the initial decision information based on the preset information processing Agent to obtain the corresponding target decision information specifically includes: Calling the information processing Agent; Based on the information processing Agent, data cleaning is performed on the initial decision information to obtain corresponding first decision information; Performing format conversion processing on the first decision information to obtain corresponding second decision information; performing feature extraction processing on the second decision information to obtain corresponding third decision information; The third decision information is used as the target decision information.

4. The query processing method based on artificial intelligence according to claim 1, characterized in that: The step of performing standard operating procedure matching processing on the target decision information based on the preset retrieval matching Agent to obtain the target standard operating procedure corresponding to the target decision information specifically includes: Calling the retrieval matching Agent; Based on the retrieval matching Agent, a preset similarity algorithm is used to calculate the similarity between the target decision information and all preset standard operating procedures; Filter out a first standard operating procedure having a similarity greater than a preset similarity threshold from all the standard operating procedures; Determining whether the number of the first standard operating procedures is greater than 1; If so, generating a comprehensive evaluation score for each of the first standard operating procedures based on the priority, feedback effect, and execution efficiency of each of the first standard operating procedures; Selecting the second standard operating procedure with the highest comprehensive evaluation score from all the first standard operating procedures; The second standard operating procedure is used as the target standard operating procedure.

5. The query processing method based on artificial intelligence according to claim 4, characterized in that: The step of generating a comprehensive evaluation score of each of the first standard operating procedures based on the priority, feedback effect, and execution efficiency of each of the first standard operating procedures specifically includes: Obtaining a specified priority, a specified feedback effect, and a specified execution efficiency of a specified standard operating procedure; wherein the specified standard operating procedure is any one of all the first standard operating procedures; generating a designated priority value corresponding to the designated priority based on a preset priority mapping table, and generating a designated feedback effect value corresponding to the designated feedback effect based on a preset effect mapping table; Determine the target weight selection algorithm; Generate a first weight, a second weight, and a third weight corresponding to the priority, the feedback effect, and the execution efficiency, respectively, based on the target weight selection algorithm; Calculate the specified priority value, the specified feedback effect value, the specified execution efficiency, the first weight, the second weight, and the third weight based on a preset evaluation calculation formula to obtain a corresponding calculation score; The calculated score is used as the comprehensive evaluation score of the designated standard operating procedure.

6. The query processing method based on artificial intelligence according to claim 1, characterized in that: The step of generating decision reply information corresponding to the query information based on the preset decision reply Agent according to the target standard operating procedure specifically includes: Calling the decision reply Agent; Determine the target information type; Based on the decision reply Agent, filtering content information corresponding to the target information type from the target standard operating procedure; Convert the content information based on a preset format to obtain corresponding target content information; The decision reply information is generated based on the target content information.

7. The query processing method based on artificial intelligence according to claim 6, characterized in that: The step of generating the decision reply information based on the target content information specifically includes: Performing grammar checking on the target content information; If the target content information passes the syntax check, then a semantic check is performed on the target content; If the target content information passes the semantic check, then performing a logical check on the target content; If the target content information passes the logic check, the target content information is used as the decision reply information.

8. A query processing device based on artificial intelligence, characterized in that: include: A receiving module, used for receiving query information input by a user; A parsing module, used to parse the query information based on a preset user interaction agent to obtain query keywords and user intentions corresponding to the query information; A collection module, used to collect initial decision information corresponding to the query keyword and the user intention based on a preset information collection agent; A processing module, used to process the initial decision information based on a preset information processing Agent to obtain corresponding target decision information; A matching module, used for performing standard operating procedure matching processing on the target decision information based on a preset retrieval matching Agent to obtain a target standard operating procedure corresponding to the target decision information; A generating module, configured to generate decision reply information corresponding to the query information based on a preset decision reply Agent and according to the target standard operating procedure; The sending module is used to send the decision reply information to the user through the user interaction Agent.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the query processing method based on artificial intelligence as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the artificial intelligence-based query processing method according to any one of claims 1 to 7 are implemented.

Images