Order processing method, system and device, storage medium and program product

Abstract

The invention discloses an order processing method, system and device, a storage medium and a program product, and relates to the technical field of natural language processing, and the method comprises the steps: receiving an order statistics request initiated by a user, and carrying out the intention recognition of the order statistics request through a preset AI agent, so as to determine the query intention of the user; performing parameter analysis on the order statistics request based on the query intention to obtain a corresponding query parameter; according to the query parameters, retrieving order statistical data meeting a preset query condition from a preset database; and outputting the order statistical data according to a preset modal form. According to the method, efficient integration and analysis of hotel order data are realized through a multi-modal data acquisition and processing technology; the business value in the order data is deeply mined through a semantic understanding and analysis technology, and a more accurate statistical result is provided for a user; and through a multi-modal output technology, various data display forms are supported, and the requirements of different users on data visualization and multi-dimensional analysis are met.

Description

Technical Field

[0001] The present application relates to the field of natural language processing technology, and in particular to an order processing method, system, device, storage medium, and program product. Background Art

[0002] In the current hotel industry, traditional order statistics and report generation methods rely primarily on manual operations or fixed statistical tools. This approach is not only inefficient but also requires a certain level of technical background and expertise, making it difficult to meet the needs of ordinary users. Furthermore, existing statistical tools typically only support fixed statistical dimensions (such as by time, city, or order type), and cannot flexibly adapt to the diverse needs of users.

[0003] As natural language processing technology is increasingly being applied to the hotel industry, some hotel application systems have begun attempting to automate order statistics through semantic understanding technology. However, these systems still suffer from significant deficiencies in terms of semantic understanding accuracy, data processing efficiency, and output format diversity. For example, existing systems struggle to accurately understand complex natural language user queries and often require long response times during data processing, failing to meet real-time requirements. Furthermore, these systems are often limited to a single output format (such as text or tables), making it difficult to meet user demands for multimodal output.

[0004] More critically, existing order statistics and report generation systems suffer from significant shortcomings in user interaction. Users must use technical query statements or complex user interfaces to complete statistical needs, significantly increasing user costs and limiting the system's widespread adoption and application. Therefore, achieving efficient and accurate order statistics and outputting results in multiple formats has become a pressing issue for the hotel industry. Summary of the Invention

[0005] The main purpose of this application is to provide an order processing method, system, device, storage medium and program product, aiming to solve the technical problem of how to efficiently and accurately realize hotel order statistics and output the results in a multimodal form.

[0006] To achieve the above objectives, the present application proposes an order processing method, which includes:

[0007] Receive an order statistics request initiated by a user and perform intent recognition on the order statistics request through a preset AI agent to determine the user's query intent;

[0008] Perform parameter parsing on the order statistics request based on the query intent to obtain corresponding query parameters;

[0009] Retrieving order statistics that meet preset query conditions from a preset database based on the query parameters;

[0010] The order statistics data are output in a preset modal form.

[0011] In one embodiment, the step of receiving an order statistics request initiated by a user and performing intent recognition on the order statistics request by a preset AI agent to determine the user's query intent information includes:

[0012] Receiving an order statistics request initiated by a user, and identifying a natural language text input by the user in the order statistics request;

[0013] The natural language text is subjected to intent recognition by a preset AI agent to identify the user's query intent.

[0014] In one embodiment, the step of performing parameter parsing on the order statistics request based on the query intent to obtain corresponding query parameters includes:

[0015] The preset AI agent performs parameter parsing on the order statistics request based on the query intent, and extracts key parameter information from the natural language text;

[0016] The key parameter information is converted into structured query parameters.

[0017] In one embodiment, the step of retrieving order statistics data that meet preset query conditions from a preset database according to the query parameters includes:

[0018] Sending a query request to the preset database, wherein the query request includes a query condition constructed based on the query parameter;

[0019] Data retrieval is performed in the preset database according to the query condition to obtain order statistics data that meet the query condition.

[0020] In one embodiment, the step of performing data retrieval in the preset database according to the query condition to obtain order statistics data that meets the preset query condition includes:

[0021] Parsing the query conditions in the query request and extracting field parameters for filtering order data, wherein the field parameters include at least one of order status, time range, or regional information;

[0022] Based on the field parameters, a matching query is performed on the order data in the preset database to obtain order data that meets the query conditions;

[0023] The order data meeting the query condition is counted to obtain order statistical data meeting the preset query condition.

[0024] In an embodiment, the step of outputting the order statistical data in a preset modal form comprises:

[0025] The order statistical data is analyzed and arranged by the preset AI agent, output content meeting the preset modal form is generated, and the output content is returned to the user end.

[0026] In addition, to achieve the above-mentioned purpose, the present application also provides an order processing system, which comprises:

[0027] An intent recognition module is configured to receive an order statistical request initiated by a user, and perform intent recognition on the order statistical request by a preset AI agent to determine the query intent of the user.

[0028] An analysis module is configured to perform parameter analysis on the order statistical request based on the query intent to obtain corresponding query parameters.

[0029] A query module is configured to retrieve order statistical data meeting a preset query condition from a preset database according to the query parameters.

[0030] An output module is configured to output the order statistical data in a preset modal form.

[0031] In addition, to achieve the above-mentioned purpose, the present application also provides an order processing device, which comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the order processing method as described above.

[0032] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, the computer program being executed by a processor to implement the steps of the order processing method as described above.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which comprises a computer program, the computer program being executed by a processor to implement the steps of the order processing method as described above.

[0034] This application proposes an order processing method, system, device, storage medium and program product. The method includes: receiving an order statistics request initiated by a user, and performing intent recognition on the order statistics request through a preset AI agent to determine the user's query intention; performing parameter parsing on the order statistics request based on the query intention to obtain corresponding query parameters; retrieving order statistics that meet the preset query conditions from a preset database based on the query parameters; and outputting the order statistics in a preset modal form. This method achieves efficient integration and analysis of hotel order data through multimodal data collection and processing technology; deeply mines the business value in order data through semantic understanding and analysis technology to provide users with more accurate statistical results; and supports multiple data display forms through multimodal output technology to meet the needs of different users for data visualization and multi-dimensional analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0037] Figure 1 A flowchart of the first embodiment of the order processing method of this application is provided;

[0038] Figure 2 A flowchart of the second embodiment of the order processing method of this application is provided;

[0039] Figure 3 A schematic diagram of a simplified process for processing an order according to the first embodiment of the present invention;

[0040] Figure 4 This is a schematic diagram of the module structure of the order processing system according to an embodiment of the present application;

[0041] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the order processing method in the embodiment of the present application.

[0042] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0044] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the drawings and specific embodiments of the specification.

[0045] The main solution of the embodiment of the present application is: receiving a user-initiated order statistics request, and identifying the intention of the order statistics request through a preset AI agent to determine the user's query intention; based on the query intention, the order statistics request is parsed to obtain the corresponding query parameters; according to the query parameters, the order statistics data that meets the preset query condition is retrieved from the preset database; and the order statistics data is output in a preset modal form.

[0046] In this embodiment, for the sake of description, the following describes the order statistics and report generation system as the execution subject.

[0047] Because the existing hotel order statistics and report generation system has deficiencies in data processing efficiency, semantic understanding ability and output form: when processing hotel order data, the data sources are diverse and the formats are not unified, resulting in low statistical efficiency; lacking deep semantic understanding of order data, it is difficult to mine the business value behind the data; the report generation form is single, and cannot meet the needs of different users for data visualization and multi-dimensional analysis.

[0048] The present application provides a solution, which can accurately parse the multi-modal order data input by the user by constructing a semantic understanding model based on natural language processing and deep learning, and combine statistical analysis algorithm to analyze and mine the hotel order data in multiple dimensions. At the same time, the system supports flexible report generation function, can automatically generate statistical reports of multiple formats according to user needs, and provides data visualization display, helps business personnel to quickly obtain key information, and improves decision-making efficiency. The core advantage of the present application lies in its multi-modal data processing capability, intelligent semantic understanding and efficient statistical analysis function, which can significantly improve the efficiency and accuracy of hotel order statistics and report generation, and provide strong data support for hotel business operation.

[0049] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as tablet computers, personal computers, mobile phones, etc., or an electronic device capable of realizing the above functions. The following takes a personal computer as an example to describe the present embodiment and each of the following embodiments.

[0050] Based on this, the present application provides an order processing method, which is described in detail with reference to Figure 1 , Figure 1 is a flowchart of the first embodiment of the order processing method of the present application.

[0051] In this embodiment, the order processing method includes steps S10 to S40:

[0052] Step S10: receiving an order statistics request initiated by a user, and performing intent recognition on the order statistics request through a preset AI agent to determine the user's query intention;

[0053] It should be noted that the preset AI agent is a pre-configured and trained intelligent semantic analysis model. It performs semantic understanding and intent classification on the text or voice information input by the user based on natural language processing technology, thereby identifying the order information the user wants to obtain.

[0054] It is understandable that due to differences in the understanding of order statistical dimensions and indicators among different users, directly executing database queries may lead to biased results. Therefore, executing step S10 can accurately understand the semantics of user requests based on the AI ​​agent, ensuring that subsequent query logic is consistent with the user's actual needs.

[0055] In a feasible embodiment, step S10 may include steps S11 to S12:

[0056] Step S11, receiving an order statistics request initiated by a user, and identifying a natural language text input by the user in the order statistics request;

[0057] Specifically, the user initiates an order statistics request in the operating application through the smart device and enters natural language text to describe the statistical requirements, for example: "I want to check the number of pre-order orders in the East China region in the past three days", where the natural language text includes but is not limited to descriptions of the time range, geographical range, order status, product type, etc.

[0058] When the operating application receives the user's input request, the natural language text content in the order statistics request is transmitted to the AI ​​agent through a preset application programming interface (API) for subsequent semantic analysis and intent recognition processing by the AI ​​agent.

[0059] Step S12: performing intent recognition on the natural language text through a preset AI agent to identify the user's query intent.

[0060] The AI ​​agent uses pre-trained natural language understanding models, such as intent recognition models based on BERT, ERNIE, or Transformer architecture, to extract features and classify the natural language text entered by the user, and identify the user's actual query intent, such as "view order statistics."

[0061] Through the above steps, the unstructured order statistics requests entered by users in natural language can be converted into structured query intention information, which not only improves the system's intelligent interaction capabilities, but also effectively improves the accuracy and response efficiency of order data query and statistical analysis.

[0062] Step S20: parsing the order statistics request based on the query intent to obtain corresponding query parameters;

[0063] It is understandable that since the natural language texts input by users are mostly unstructured texts and lack standardized expressions, direct use for database queries will result in problems such as semantic ambiguity and inconsistent formats, which can easily lead to misunderstandings or retrieval failures when performing order statistics. Therefore, by executing step S20, the natural language text can be semantically parsed by the AI ​​agent and converted into structured query parameters, which is conducive to improving the accuracy of subsequent order statistical data retrieval and the system response efficiency.

[0064] In a feasible implementation, step S20 may include steps S21 to S23:

[0065] Step S21: performing parameter parsing on the order statistics request based on the query intent by the preset AI agent, and extracting key parameter information from the natural language text;

[0066] Specifically, through the preset AI agent, after identifying the user's query intention, it further performs parameter parsing on the natural language text in the order statistics request initiated by the user to extract structured key information related to order statistics.

[0067] For example, when a user enters a request such as "I want to check the number of pre-orders in the East China region in the past three days", the AI ​​agent performs semantic analysis on the sentence based on the natural language processing model and extracts key parameters of multiple dimensions, including the time range "the past three days", the regional information "East China region", and the order status "pre-order" and other key information.

[0068] Through the above steps, the key information extracted will be used as the core screening conditions for subsequent database queries to build structured query statements, thereby achieving accurate retrieval and statistical analysis of target order data.

[0069] Step S22: convert the key parameter information into structured query parameters.

[0070] In order to make the input natural language text adapt to the database query format and improve the retrieval accuracy, this step uses the preset AI agent to standardize the parsed key parameter information and convert it into structured query parameters with unified field definitions and data formats.

[0071] For example, when the key parameters parsed from a user request include the time range "past three days," the region "East China," and the order status "pre-ordered," the AI ​​agent calculates the specific time interval based on the system's current time (e.g., January 20, 2025) and generates the corresponding start and end times. At the same time, the region information is mapped to the geocode preset in the database, ultimately forming the following structured query parameters: {"startTime":"2025-01-17", "endTime":"2025-01-19", "city":"East China", "orderStatus":"pre-ordered"}.

[0072] In the above steps, the semantic parsing model parses the order statistics request based on the user's query intent, comprehensively extracting key information from the request, significantly improving the accuracy and robustness of semantic understanding. Furthermore, the extracted key information is converted into structured query parameters with unified field definitions and data formats, which adapt to database query formats and improve retrieval accuracy.

[0073] Step S30, according to the query parameters, retrieve order statistics that meet the preset query conditions from the preset database;

[0074] It is understandable that since traditional order statistics operations usually rely on manual screening and exporting, which is not only time-consuming but also error-prone, executing step S30 can automatically call the database interface through structured query parameters to achieve intelligent retrieval and rapid aggregation of order data, significantly improving the system's automated processing capabilities and user experience.

[0075] In a feasible embodiment, step S30 may include steps S31 to S32:

[0076] Step S31, sending a query request to the preset database, wherein the query request includes a query condition constructed based on the query parameter;

[0077] Specifically, after completing the structured conversion of key parameters in the user's order motivation request, the system calls the order processor according to the generated structured query parameters, and sends a query request to the preset database through the preset data access interface, wherein the query request contains query conditions constructed by the query parameters, such as the filtering conditions formed by the combination of fields such as time range, geographical information, order status, etc., which are used to retrieve the order data set that meets the user's query requirements from the preset data.

[0078] In some embodiments, the query conditions can be further converted into standard database query languages ​​(e.g., SQL statements) to adapt to different types of database systems (e.g., MySQL, Oracle, MongoDB, etc.), thereby ensuring the compatibility and efficiency of query operations. Furthermore, the query condition construction process can be dynamically adjusted in conjunction with a business rule engine, for example, automatically expanding the query scope based on holidays or promotional periods.

[0079] By executing the above query request sending steps, the system can trigger the data matching and retrieval process on the database side, providing basic data support for subsequent acquisition of target order statistical data and performing aggregate analysis.

[0080] Step S32: performing data retrieval in the preset database according to the query condition to obtain order statistics data that meet the query condition.

[0081] It should be noted that in order to improve the efficiency of large-scale order data retrieval, this embodiment adopts a distributed database architecture and accelerates the joint query of time range and regional information by establishing a composite index.

[0082] Specifically, before executing a database search, the system first verifies the validity of the generated structured query parameters to ensure their format is complete and complies with business rules. If a query parameter is detected as missing, incorrectly formatted, or logically conflicting, the system terminates the current query and returns a corresponding prompt to the user, such as "Is the time range in a valid date format?", "Does the region information match the region code in the database?", or "Does the order status fall within the set of valid statuses defined by the system?"

[0083] If any query parameter fails the validity check, the system will record the corresponding exception information and provide feedback to the user, and can also provide correction suggestions, such as completing the default time range or recommending optional regional options.

[0084] On the contrary, for query parameters that pass the legality check, the system will perform a matching query on the order data table in the database based on the query conditions, and aggregate and analyze the order data that meets the query conditions, and finally obtain order statistics that meet the query conditions.

[0085] For example, when a user queries "the number of pre-orders in East China in the past three days," the system executes a database query and returns statistical results in the following format: {"order_num":7500}, where "order_num" represents the total number of orders that meet the query criteria. This data can be directly used for subsequent statistical analysis, visualization, or voice broadcast output.

[0086] Through the above steps, the acquisition of order statistics can provide accurate data support for subsequent data analysis, content editing and multimodal output, thereby realizing a complete closed-loop processing flow from user input to result presentation.

[0087] Furthermore, after the preset database completes retrieving order statistics that meet the query conditions, in order to ensure the timeliness and data consistency of subsequent query results, the preset database can also be updated in real time.

[0088] Specifically, the system writes the latest order data (such as new orders, order status changes, etc.) into the database by monitoring order status change events, receiving data synchronization requests from external systems, or performing data refresh tasks at regular intervals to ensure the real-time and accuracy of order statistics in the database.

[0089] In the hotel order scenario, for example, when a new user completes a reservation or an existing reservation is canceled, the system can promptly trigger the data update process and synchronize the change information to the corresponding fields in the database, thereby ensuring that subsequent statistical query results can reflect the latest business status.

[0090] By introducing a real-time update mechanism for the database, not only is the data accuracy and responsiveness of the order statistics function improved, but it also provides reliable data support for the subsequent generation of more accurate statistical results that are closer to actual business conditions.

[0091] Step S40: output the order statistics in a preset modal format.

[0092] It should be noted that the preset modal forms include but are not limited to table formats, charts, trend charts, and voice.

[0093] It is understandable that since the existing order statistics and report generation systems are usually limited to a single form (such as text or table) in output format, it is difficult to meet users' needs for multimodal output. Therefore, step S40 is executed to support multiple data display forms through multimodal output technology to meet the needs of different users for data visualization and multi-dimensional analysis.

[0094] In a feasible embodiment, step S40 may include step S41:

[0095] Step S41: Analyze and organize the order statistics data through the preset AI agent, generate output content that conforms to the preset modal form, and return the output content to the user end.

[0096] Specifically, a pre-set AI agent first performs semantic understanding and analysis on order statistics matching the query criteria, identifying key indicator trends, abnormal fluctuations, or comparative relationships. Subsequently, a natural language generation model is used to convert structured order statistics into readable and semantically clear natural language text, such as "The total number of pre-orders in East China over the past week was 6,000."

[0097] On this basis, the AI ​​agent converts the format and visualizes order statistics according to the user-specified output mode or preset display rules. When the user requires a structured data display, the system automatically generates a tabular result, such as a "Daily Order Statistics Table." When the user is interested in data trends, the AI ​​agent automatically selects the appropriate chart type based on the data characteristics, such as a "Daily Order Trend Line Chart," to visually display the changes in order volume over time.

[0098] Finally, the generated text, table or chart results are returned to the user end, completing the entire order statistics request processing flow.

[0099] Through the above steps, the template-driven intelligent report generation mechanism can automatically generate statistical reports in various formats (such as charts, tables, and text descriptions) based on the statistical results of hotel order data, effectively improving the efficiency and flexibility of hotel order data analysis and presentation.

[0100] Through the above-mentioned embodiment method, an order statistics request initiated by a user is received, and the order statistics request is identified by a preset AI agent to determine the user's query intention; the order statistics request is parameter parsed based on the query intention to obtain the corresponding query parameters; according to the query parameters, order statistics data that meet the preset query conditions are retrieved from the preset database; and the order statistics data are output in a preset modal form. This solution can accurately parse the multimodal order data input by the user by constructing a semantic understanding model based on natural language processing and deep learning, and combine it with statistical analysis algorithms to perform multi-dimensional analysis and mining of hotel order data. At the same time, the system supports flexible report generation functions, which can automatically generate statistical reports in various formats according to user needs, and provide data visualization display to help business personnel quickly obtain key information and improve decision-making efficiency. The core advantage of the present invention lies in its multimodal data processing capabilities, intelligent semantic understanding and efficient statistical analysis functions, which can significantly improve the efficiency and accuracy of order statistics and report generation, and provide strong data support for user business operations.

[0101] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2, further illustrating step S32, said step S32 further includes steps S321 to S323:

[0102] Step S321: parsing the query conditions in the query request and extracting field parameters for filtering order data, wherein the field parameters include at least one of order status, time range, or region information;

[0103] Step S322: performing a matching query on the order data in the preset database based on the field parameters to obtain order data that meets the query conditions;

[0104] Step S323 , collecting statistics on the order data that meets the query conditions to obtain statistical data on the orders that meet the preset query conditions.

[0105] Compared with the first embodiment, this embodiment further explains how to filter out order statistics that meet preset query conditions based on query data in a preset database.

[0106] Specifically, before the system invokes the order processor to initiate a query request to the pre-set database based on the query parameters, it parses the query request and extracts all relevant field parameters. These field parameters are used to filter relevant information from the database for order data that meets the query criteria. Specifically, these field parameters include, but are not limited to: order status (e.g., paid, pending shipment, completed, pre-ordered); time range (e.g., past week, last month); and geographic location information, i.e., the geographic location where the order occurred.

[0107] Once the field parameters are extracted from the query request, the order processor initiates a query request to the preset database. The preset database uses the field parameters in the query request as filtering conditions to match the order data in the preset database and obtain all order records that meet the conditions.

[0108] Finally, the qualified order data obtained is summarized and calculated based on the user's query conditions and focus (such as order quantity, total sales, etc.), thereby obtaining insightful statistical data.

[0109] The following is an example of the above steps based on the hotel order scenario.

[0110] The system receives hotel order statistics requests from users and parses them using its semantic understanding module to identify key query criteria. For example, if a user enters "View confirmed hotel orders in East China over the past week," the system extracts the following field parameters: Order Status: Confirmed; Time Range: Past Week; Region: East China. These field parameters form the core filtering criteria for subsequent database queries, ensuring that search results closely match user needs.

[0111] After extracting the field parameters, the system constructs a database query statement (such as an SQL statement) based on these structured parameters and performs a matching query operation in the preset hotel order database. For example, the system will find all order records that meet the following conditions:

[0112] The order creation time is between June 13, 2025 and June 20, 2025;

[0113] The hotel is located in "East China";

[0114] The order status is "Confirmed".

[0115] The system efficiently retrieves qualified hotel order sets through index optimization, paging processing, etc., providing raw data support for subsequent statistical analysis.

[0116] After obtaining a collection of hotel bookings that meet the query criteria, the system further compiles statistics to generate order statistics that meet the query criteria. Common statistical dimensions include, but are not limited to, order quantity statistics, total transaction amount, occupancy distribution, and room type preference statistics.

[0117] Through the above-mentioned embodiment method, the system can accurately locate and count the order data that users are interested in, providing an accurate data basis for subsequent content generation and multimodal output (such as chart display and voice broadcast), thereby improving data analysis efficiency and user experience.

[0118] For example, to help understand the implementation process of the order processing method obtained by combining this embodiment with the above embodiment 1, please refer to Figure 3 , Figure 3 A brief flowchart of an order processing method is provided, specifically:

[0119] This embodiment proposes a hotel order statistics semantic understanding and report generation system solution that supports multimodal output, including user intent recognition, key parameter analysis, hotel order data statistics, and multimodal data generation.

[0120] Specifically, users can initiate order statistics requests to the system through smart devices (such as Xiaozhao robot). The system receives the order statistics request and recognizes the natural language text entered by the user in the request, for example: "I want to check the number of pre-order orders in Shanghai in the past week."

[0121] After receiving the order statistics request initiated by the user, the application interface is called to pass the user's order statistics request to the AI ​​agent so that the AI ​​agent can recognize the natural language text in the order statistics request for intent recognition.

[0122] After receiving a user's request for order statistics, the AI ​​agent identifies the user's intent and parses out the user's core need, such as "view order statistics." The AI ​​agent then further parses the parameters of the request and extracts key information, such as the time range "past week," the region "Shanghai," and the order status "pre-ordered."

[0123] The AI ​​agent then converts the parsed key information into structured query parameters, for example, {"startTime":"2025-01-13", "endTime":"2025-01-19", "city":"Shanghai"}. Based on the parsed query parameters, the AI ​​agent calls the corresponding order processor and searches the preset database for order statistics that meet the preset query criteria, for example, {"order_num":7500}.

[0124] The AI ​​agent then analyzes and organizes the order statistics that meet the preset query criteria. For example, if the user requires a natural language description, the AI ​​agent can output text such as "The total number of pre-orders in Shanghai over the past week was 7,500." If a table is required, the AI ​​agent organizes the order data into a table format, such as "Daily Order Statistics Table." If the user wants to display the data in a chart format, the AI ​​agent can also plot the order data as a trend chart, such as "Daily Order Trend Line Chart."

[0125] Finally, the system returns the generated text, table or chart results to the user through the smart device, completing the entire order statistics request processing flow.

[0126] Through the above-mentioned embodiment method, the hotel order semantic understanding technology based on multimodal data fusion is utilized to integrate various forms of information such as text, structured data and voice. The purpose of doing so is to fully capture the key elements in the order, thereby significantly improving the accuracy and robustness of semantic understanding. At the same time, by adopting a hotel order semantic parsing model based on deep learning, and combining the attention mechanism with sequence modeling technology, important information such as time, room type, and number of people in the order can be efficiently extracted, supporting accurate parsing of complex semantic scenarios. In addition, the template-driven intelligent report generation mechanism can automatically create statistical reports in various formats including charts, tables and text descriptions based on the statistical results of hotel order data. This not only improves the efficiency of hotel order data analysis and display, but also increases its flexibility, making the transmission of information more intuitive and effective.

[0127] It should be noted that the above examples are only used to understand this application and do not constitute a limitation on the order processing method of this application. More simple transformations based on this technical concept are all within the scope of protection of this application.

[0128] This application also provides an order processing system, please refer to Figure 4 , the order processing system includes:

[0129] The intent recognition module 10 is used to receive an order statistics request initiated by a user and perform intent recognition on the order statistics request through a preset AI agent to determine the user's query intention;

[0130] A parsing module 20 is configured to perform parameter parsing on the order statistics request based on the query intent to obtain corresponding query parameters;

[0131] A query module 30 is configured to retrieve order statistics that meet preset query conditions from a preset database based on the query parameters;

[0132] The output module 40 is used to output the order statistics in a preset modal format.

[0133] The order processing system provided in this application, utilizing the order processing method described in the aforementioned embodiments, can address the technical problem of efficiently and accurately achieving hotel order statistics and outputting the results in a multimodal format. Compared to the prior art, the order processing system provided in this application offers the same beneficial effects as the order processing method described in the aforementioned embodiments. Other technical features of the order processing system are the same as those disclosed in the aforementioned embodiments and are not further elaborated upon here.

[0134] The present application provides an order processing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the order processing method in the above-mentioned embodiment one.

[0135] Reference below Figure 5 , which shows a schematic diagram of the structure of an order processing device suitable for implementing the embodiments of the present application. The order processing device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The order processing device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0136] like Figure 5 As shown, the order processing device may include a processing system 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory 1002 or programs loaded from a storage system 1003 into a random access memory 1004. Random access memory 1004 also stores various programs and data required for the operation of the order processing device. Processing system 1001, read-only memory 1002, and random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems may be connected to the input / output interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 can allow the order processing device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows an order processing device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have alternatively.

[0137] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication system, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0138] The order processing device provided in this application, utilizing the order processing method described in the aforementioned embodiment, can address the technical problem of efficiently and accurately achieving hotel order statistics and outputting the results in a multimodal format. Compared to the prior art, the order processing device provided in this application achieves the same beneficial effects as the order processing method described in the aforementioned embodiment. Other technical features of this order processing device are the same as those disclosed in the aforementioned embodiment and are not further elaborated upon here.

[0139] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0140] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0141] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer program) stored thereon, and the computer-readable program instructions are used to execute the order processing method in the above embodiment.

[0142] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0143] The computer-readable storage medium may be included in the order processing device, or may exist independently without being incorporated into the order processing device.

[0144] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the order processing device, the order processing device enables the following: to receive an order statistics request initiated by a user, and to perform intent recognition on the order statistics request through a preset AI intelligent agent to determine the user's query intention; to perform parameter parsing on the order statistics request based on the query intention to obtain corresponding query parameters; to retrieve order statistics data that meet the preset query conditions from a preset database according to the query parameters; and to output the order statistics data in a preset modal form.

[0145] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0146] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0147] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0148] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned order processing method. This computer-readable storage medium addresses the technical problem of efficiently and accurately achieving hotel order statistics and outputting the results in a multimodal format. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the order processing method provided in the aforementioned embodiments, and are not further elaborated here.

[0149] The present application also provides a computer program product, comprising a computer program, which implements the steps of the order processing method described above when executed by a processor.

[0150] The computer program product provided in this application solves the technical problem of efficiently and accurately implementing hotel order statistics and outputting the results in a multimodal format. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the order processing method provided in the above-mentioned embodiment, and are not further elaborated here.

[0151] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An order processing method, characterized in that: The order processing method includes: Receive an order statistics request initiated by a user and perform intent recognition on the order statistics request through a preset AI agent to determine the user's query intent; Perform parameter parsing on the order statistics request based on the query intent to obtain corresponding query parameters; Retrieving order statistics that meet preset query conditions from a preset database based on the query parameters; The order statistics data are output in a preset modal form.

2. The order processing method according to claim 1, wherein: The step of receiving an order statistics request initiated by a user and performing intent recognition on the order statistics request by a preset AI agent to determine the user's query intention information includes: Receiving an order statistics request initiated by a user, and identifying a natural language text input by the user in the order statistics request; The natural language text is subjected to intent recognition by a preset AI agent to identify the user's query intent.

3. The order processing method according to any one of claims 1 to 2, characterized in that: The step of performing parameter parsing on the order statistics request based on the query intent to obtain corresponding query parameters includes: The preset AI agent performs parameter parsing on the order statistics request based on the query intent, and extracts key parameter information from the natural language text; The key parameter information is converted into structured query parameters.

4. The order processing method according to claim 1, wherein: The step of retrieving order statistics data that meet the preset query conditions from the preset database according to the query parameters includes: Sending a query request to the preset database, wherein the query request includes a query condition constructed based on the query parameter; Data retrieval is performed in the preset database according to the query condition to obtain order statistics data that meet the query condition.

5. The order processing method according to claim 4, wherein: The step of performing data retrieval in the preset database according to the query condition to obtain order statistics data that meets the preset query condition includes: Parsing the query conditions in the query request and extracting field parameters for filtering order data, wherein the field parameters include at least one of order status, time range, or regional information; Based on the field parameters, a matching query is performed on the order data in the preset database to obtain order data that meets the query conditions; The order data meeting the query condition is counted to obtain the order statistical data meeting the preset query condition.

6. The order processing method according to claim 1, wherein: The step of outputting the order statistics data in a preset modal form includes: The order statistics data are analyzed and compiled by the preset AI agent to generate output content that conforms to the preset modal form, and the output content is returned to the user end.

7. An order processing system, characterized in that: The order processing system includes: An intent recognition module is used to receive an order statistics request initiated by a user and perform intent recognition on the order statistics request through a preset AI agent to determine the user's query intention; A parsing module, configured to parse parameters of the order statistics request based on the query intent to obtain corresponding query parameters; A query module, configured to retrieve order statistics that meet preset query conditions from a preset database based on the query parameters; The output module is used to output the order statistics in a preset modal form.

8. An order processing device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the order processing method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the order processing method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the order processing method according to any one of claims 1 to 6 are implemented.

Images