Data processing method and computing device

Abstract

The embodiment of the invention provides a data processing method and computing device.The data processing method is applied to a server side and comprises the steps that in response to an item query instruction, sent by a client side, of a target object, a target query item is determined according to the item query instruction; obtaining at least one item query department corresponding to the target query item by utilizing a large language model; determining a target query mechanism, a target project query department in the target query mechanism and a target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department; returning the target query mechanism, a target project query department in the target query mechanism and a target project query object in the target project query department to the client; at least one corresponding item query department can be determined for the target query item, and efficient ordering decision guidance is provided according to the object attribute information and the at least one item query department.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of computer technology, and in particular, to a data processing method. Background Art

[0002] As people pay more attention to health management, users have an increasing need to seek further medical treatment for diagnosis when they find abnormal results after a physical examination. However, when users need to undergo an examination, they are often confused about the choice of specific department.

[0003] For example, the same examination application for "thyroid color ultrasound examination" can be issued in different departments (such as head and neck surgery, general surgery, thyroid department, and otolaryngology department), but users lack effective information to judge and choose; and the current medical systems related to registration services have failed to effectively match user needs with reasonable and executable departments, resulting in a waste of time and energy for users during the registration process. Summary of the invention

[0004] In view of this, the embodiments of this specification provide three data processing methods. One or more embodiments of this specification also involve two data processing devices, a data processing system, a computing device, a computer-readable storage medium and a computer program product to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a data processing method is provided, which is applied to a server, and includes:

[0006] In response to a project query instruction of a target object sent by a client, determining a target query project according to the project query instruction;

[0007] Using a large language model, obtaining at least one project query department corresponding to the target query project;

[0008] Determine a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet a preset condition;

[0009] The target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are returned to the client.

[0010] According to a second aspect of an embodiment of this specification, a data processing method is provided, which is applied to a client and includes:

[0011] Receive query data of the target object, and send a project query instruction of the target object to the server according to the query data;

[0012] Receive and display the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department, returned by the server according to the project query instruction.

[0013] Among them, the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are determined by the server according to the above-mentioned data processing method.

[0014] According to a third aspect of the embodiments of this specification, a data processing method is provided, which is applied to a data processing system, wherein the data processing system includes a client and a server, wherein:

[0015] The client receives query data of the target object, and sends a project query instruction of the target object to the server according to the query data;

[0016] The server, in response to a project query instruction of the target object sent by the client, determines a target query project according to the project query instruction, obtains at least one project query department corresponding to the target query project by using a large language model, determines a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department according to object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet a preset condition, and returns the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department to the client;

[0017] The client receives and displays the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server.

[0018] According to a fourth aspect of an embodiment of this specification, a data processing device is provided, which is applied to a server, including:

[0019] The project determination module is configured to respond to the project query instruction of the target object sent by the client and determine the target query project according to the project query instruction;

[0020] A department acquisition module is configured to obtain at least one project query department corresponding to the target query project by using a large language model;

[0021] A target determination module is configured to determine a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet a preset condition;

[0022] The data sending module is configured to return the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department to the client.

[0023] According to a fifth aspect of the embodiments of this specification, there is provided a data processing device, applied to a client, comprising:

[0024] An instruction sending module is configured to receive query data of a target object, and send an item query instruction of the target object to a server according to the query data;

[0025] The data receiving module is configured to receive and display the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server according to the project query instruction, wherein the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are determined by the server according to the above-mentioned data processing method.

[0026] According to a sixth aspect of the embodiments of this specification, a data processing system is provided, including a client and a server, wherein:

[0027] The client is used to receive query data of the target object and send a project query instruction of the target object to the server according to the query data;

[0028] The server is used to respond to a project query instruction of the target object sent by the client, determine the target query project according to the project query instruction, obtain at least one project query department corresponding to the target query project by using a large language model, determine the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet a preset condition, and return the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department to the client;

[0029] The client is used to receive and display the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server.

[0030] According to a seventh aspect of an embodiment of this specification, a computing device is provided, including:

[0031] Memory and processor;

[0032] The memory is used to store computer programs / instructions, and the processor is used to execute computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the above-mentioned data processing method are implemented.

[0033] According to an eighth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores a computer program / instruction, and the computer program / instruction implements the steps of the above-mentioned data processing method when executed by a processor.

[0034] According to a ninth aspect of the embodiments of this specification, there is provided a computer program product, comprising a computer program / instruction, which implements the steps of the above-mentioned data processing method when executed by a processor.

[0035] An embodiment of the present specification provides a data processing method applied to a server, which responds to a project query instruction of a target object sent by a client, determines a target query project corresponding to the target object according to the project query instruction, and efficiently and accurately determines at least one project query department corresponding to the target query project through a large language model, and the target object needs to be registered based on a query agency or a project query object. Therefore, according to the object attribute information of the target object and at least one project query department, a target query agency with a target project query department (one or more project query departments in at least one project query department that meet preset conditions), a target project query department in the target query agency, and a target project query object in the target project query department are determined. The target query agency selects a target project query department from at least one project query department based on the object attribute information of the target object and the preset conditions. When the target query agency is determined in the department, the target query agency can better match the needs of the target object, and by returning the target query agency, the target project query department in the target query agency, and the target project query object in the target project query department to the client, the target query agency, the target project query department in the target query agency, and the target project query object in the target project query department can be displayed on the client, thereby providing efficient order decision guidance, improving the appointment conversion rate, and reducing the waste of time and resources caused by improper selection of the target object. In addition, when the target query agency is displayed on the client, the target project query department in the target query agency is displayed instead of other project query departments unrelated to the target query project, so that the target object can directly and clearly understand the target project query department related to the target query project in the target query agency, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a scenario diagram of a data processing method provided by an embodiment of this specification;

[0037] Figure 2 is a flow chart of a data processing method applied to a server provided by an embodiment of this specification;

[0038] Figure 3 is a flow chart of a data processing method applied to a client provided by an embodiment of this specification;

[0039] Figure 4 is a flow chart of a data processing method applied to a data processing system provided by one embodiment of the present specification;

[0040] Figure 5 is a schematic diagram of a user interaction interface provided by an embodiment of this specification;

[0041] Figure 6is another schematic diagram of a user interaction interface provided by an embodiment of this specification;

[0042] Figure 7 is a structural schematic diagram of a data processing device provided by an embodiment of this specification;

[0043] Figure 8 is a schematic diagram of the structure of another data processing device provided by an embodiment of this specification;

[0044] Fig. 9 is a structural diagram of a data processing system provided by an embodiment of this specification;

[0045] Fig.10 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0046] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0047] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0048] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0049] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0050] In one or more embodiments of this specification, a large model refers to a deep learning model with large-scale model parameters, which usually contains hundreds of millions, tens of billions, hundreds of billions, trillions, or even more than 10 trillion model parameters. A large model can also be called a foundation model / foundation model (Foundation Model 1). The large model is pre-trained with large-scale unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks, and the model has good generalization ability, such as a large-scale language model (LLM, Large Language Model 1), a multi-modal pre-training model (multi-modal pre-training model 1), etc.

[0051] When the big model is used in practice, only a small number of samples are needed to fine-tune the pre-trained model and it can be applied to different tasks. The big model can be widely used in natural language processing (NLP), computer vision and other fields. Specifically, it can be applied to computer vision tasks such as visual question answering (VQA), image description (IC), image generation, as well as natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. The main application scenarios of the big model include digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc.

[0052] First, the terms involved in one or more embodiments of this specification are explained.

[0053] One-to-many mapping between examinations and departments: In medical information systems, "one-to-many mapping between examinations and departments" is usually used to describe a data relationship in which one examination item may be evaluated or processed by multiple departments. For example, a patient may need an electrocardiogram, which can be performed in multiple departments such as cardiology and internal medicine. This mapping relationship can help hospitals manage the patient's examination process, allocate resources more efficiently, and improve work efficiency.

[0054] AI (Artificial Intelligence) semantic recognition: AI semantic understanding and recognition is one of the core technologies in the field of artificial intelligence, which aims to enable computers to understand the meaning and context of human language; it involves multiple tasks in natural language processing, such as semantic analysis, intent recognition, entity recognition, etc.

[0055] Natural language: Natural language refers to the language that humans use naturally in daily communication, such as English, Chinese, French, etc. Unlike artificial languages ​​(such as programming languages), natural languages ​​are complex and ambiguous, including multiple levels such as syntax, semantics, and pragmatics.

[0056] As people pay more attention to health management, users are increasingly seeking medical advice for diagnosis after physical examinations due to abnormal physical examination results. Users face two main challenges in this process:

[0057] Complexity of one-to-many mapping between examinations and departments: When users need to undergo an examination, they are often confused about the choice of specific departments. For example, for "thyroid color Doppler ultrasound examination", the same examination application can be issued in different departments (such as head and neck surgery, general surgery, thyroid department, and otolaryngology department), but users lack effective information to judge and choose.

[0058] Lack of information matching: The current medical systems related to registration services have failed to effectively match user needs with executable departments, resulting in a waste of time and energy for users during the registration process.

[0059] In order to solve the above technical problems, three data processing methods are provided in this specification. This specification also involves two data processing devices, a data processing system, a computing device, a computer-readable storage medium, and a computer program product, which are described in detail one by one in the following embodiments.

[0060] See also Figure 1 , Figure 1 A scenario diagram of a data processing method provided according to an embodiment of the present specification is shown.

[0061] In such Figure 1 In the application scenario shown, the large model is deployed in the server 104, and the server 104 can be connected to one or more end-side devices 102 through a local area network connection, a wide area network connection, an Internet connection, or other types of data networks. The end-side device 102 here may include but is not limited to: smart phones, tablet computers, laptops, PDAs, personal computers, smart home devices, vehicle-mounted devices, etc. The end-side device 102 can interact with the user through a graphical user interface to call the large model, thereby implementing the method provided in the embodiments of this specification.

[0062] In the embodiments of this specification, the data processing systems of the client and the server can perform the following steps:

[0063] The client is used to receive the query data of the target object and send the project query instruction of the target object to the server according to the query data;

[0064] A server, for responding to a project query instruction of the target object sent by a client, determining a target query project according to the project query instruction, obtaining at least one project query department corresponding to the target query project by using a large language model, determining a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department according to object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet a preset condition, and returning the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department to the client;

[0065] The client is used to receive and display the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department (i.e., the recommendation result). The specific display method of the client displaying the recommendation result can be found in Figure 1 ).

[0066] It should be noted that, when the operating resources of the client device can meet the deployment and operating conditions of the large model, the embodiments of the present application can be carried out in the client device.

[0067] An embodiment of the present specification provides a data processing method applied to a server, which responds to a project query instruction of a target object sent by a client, determines a target query project corresponding to the target object according to the project query instruction, and efficiently and accurately determines at least one project query department corresponding to the target query project through a large language model, and the target object needs to be registered based on a query agency or a project query object. Therefore, according to the object attribute information of the target object and at least one project query department, a target query agency with a target project query department (one or more project query departments in at least one project query department that meet preset conditions), a target project query department in the target query agency, and a target project query object in the target project query department are determined. The target query agency selects a target project query department from at least one project query department based on the object attribute information of the target object and the preset conditions. When the target query agency is determined in the department, the target query agency can better match the needs of the target object, and by returning the target query agency, the target project query department in the target query agency, and the target project query object in the target project query department to the client, the target query agency, the target project query department in the target query agency, and the target project query object in the target project query department can be displayed on the client, thereby providing efficient order decision guidance, improving the appointment conversion rate, and reducing the waste of time and resources caused by improper target object selection. In addition, when the target query agency is displayed on the client, the target project query department in the target query agency is displayed instead of other project query departments unrelated to the target query project, so that the target object can directly and clearly understand the target project query department related to the target query project in the target query agency, thereby improving the user experience.

[0068] See also Figure 2 , Figure 2 A flow chart of a data processing method applied to a server provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0069] Step 202: In response to an item query instruction of a target object sent by a client, a target query item is determined according to the item query instruction.

[0070] Among them, the target object can be understood as the object to be inspected, such as a person or a pet, without limitation here, and the corresponding target query item is determined for the target object; the item query instruction can be understood as the specific request sent by the client, which is used to query or obtain the target query item corresponding to the target object; the target query item can be understood as the inspection item that the target object queries and wants to inspect.

[0071] Specifically, when receiving a project query instruction for a target object sent by the client, the server determines the target query item corresponding to the project query instruction, that is, determines the inspection item that the target object queries and wants to inspect, thereby recommending subsequent information based on the target query item.

[0072] In one or more embodiments of the present specification, the project query instruction sent by the client may directly carry the project information of the target query project. For example, the query data of the target object is processed in the client to determine the target query project. Therefore, the project query instruction sent by the client may directly carry the project information of the target query project. Alternatively, the target object is input as the target query project in the client. In this case, the project query instruction sent by the client may directly carry the target query project. This is not limited here. The specific implementation is as follows:

[0073] Determining the target query item according to the item query instruction includes:

[0074] The target query item is determined according to the item information of the target query item carried in the item query instruction.

[0075] Among them, project information can be understood as various data related to the project. For example, project information includes but is limited to project name, project number, etc. The project information is used to identify a specific project. Therefore, the project information needs to be unique, that is, based on the project information, the target query project corresponding to the project information can be determined.

[0076] Specifically, when the item query instruction sent by the client carries the item information of the target query item, the corresponding target query item can be directly determined based on the item information.

[0077] In actual applications, when the data processing method is applied to medical registration scenarios, the target query item is the item that the user wants to examine. For example, when the project information is the project name, the project query instruction sent by the client carries the project name of "thyroid color ultrasound examination", and directly determines that the target query item of the target object is "thyroid color ultrasound examination".

[0078] In one or more embodiments of the present specification, the project query instruction does not carry specific project information, but carries query data of the target object. In this case, semantic recognition is performed on the query data, so as to determine the target query project based on the semantic recognition result. The specific implementation is as follows:

[0079] Determining the target query item according to the item query instruction includes:

[0080] The query data of the target object carried in the item query instruction is determined, and semantic recognition is performed on the query data to determine the target query item.

[0081] The query data can be understood as a natural language query question or query document, which is used to determine the query requirements of the target object. For example, the query data can be "which department should I go to for a thyroid color Doppler ultrasound examination".

[0082] Specifically, the project query instruction of the target object carries the query data of the target object, and the target query project corresponding to the query data is determined by performing semantic recognition on the query data, such as semantic analysis, intent recognition, entity recognition, etc.

[0083] In one or more embodiments of this specification, in order to efficiently and accurately determine the corresponding target query item based on the query data, a large language model is used to perform semantic recognition on the query data. The specific implementation is as follows:

[0084] The performing semantic recognition on the query data to determine the target query item includes:

[0085] The query data is input into the large language model, and the large language model is used to perform semantic recognition on the query data to determine the target query item.

[0086] Among them, the large language model can be understood as an artificial intelligence model that is trained with a large amount of data and aims to understand and generate natural language text.

[0087] Specifically, the query data is input into the big language model. When the query data contains the target query item, the big language model is used to perform entity recognition to determine the target query item. For example, using the above example, when the query data is "Which department should I go to for thyroid color ultrasound examination", the entity keyword "thyroid color ultrasound examination" is identified from the natural language, thereby determining that the target query item is "thyroid color ultrasound examination".

[0088] When the query data is "If I want to do a thyroid color ultrasound, which department should I go to?" or "If I have a problem with my thyroid, which department should I register for a color ultrasound?", the large language model is used to perform semantic understanding and intent analysis on the query data, thereby identifying that the target query item corresponding to the query data is "thyroid color ultrasound examination."

[0089] The data processing method provided in the embodiments of this specification, by inputting query data into a large language model, can utilize the large language model's processing capabilities for natural language text to efficiently and accurately perform entity recognition, semantic understanding, intent analysis, and other processing on the query data, thereby accurately determining the target query items of the target object.

[0090] In one or more embodiments of the present specification, the query data may be a query question or a query document, and for different types of query data, a natural language processing model that is more compatible with the query question may be used to process the query question, and a document parsing model that is more compatible with the query document may be used to parse the query document, thereby improving the accuracy and efficiency of determining the target query item. The specific implementation is as follows:

[0091] The step of inputting the query data into the large language model, performing semantic recognition on the query data using the large language model, and determining the target query item includes:

[0092] When it is determined that the query data is a query question, a natural language processing model is used to perform semantic recognition on the query question to determine a target query item corresponding to the query question; or

[0093] When it is determined that the query data is a query document, a document parsing model is used to perform semantic recognition on the query document to determine a target query item corresponding to the query document.

[0094] Using the above example, in the medical registration scenario, we will take two cases as examples. The first case: when the user feels uncomfortable or wants to undergo routine examination, he chooses to register online and then go to the hospital for project examination. The second case: when the user receives the physical examination report and finds that there is an early warning for abnormal parts in the physical examination report (for example, the physical examination report indicates thyroid nodules, reminding the user to go to the hospital for further confirmation examination), the user wants to seek further medical treatment for the abnormal part, so he needs to register online in advance.

[0095] At this time, for the first case mentioned above, the query data can be a query question, such as the user enters the query question in the search bar of the client interface to determine the corresponding target query item; for the second case mentioned above, the query data can be a query question or a query document, and the query document at this time is the physical examination report.

[0096] Specifically, when the query data is a query question, the query question is usually a relatively brief, natural language text that contains the user's query intention and the required information. Therefore, the natural language processing model can be used to perform semantic analysis, intent recognition and other processing on the query question to determine the target query item corresponding to the query question; and when the query data is a query document, the query document usually contains structured text. At this time, the document parsing model can be used to perform document parsing on the query text, thereby extracting the abnormal part pointed out in the query document, and determining the corresponding target query item based on the specific abnormal part, to achieve more comprehensive and efficient parsing.

[0097] Of course, in actual applications, when the natural language processing model has the ability to parse documents, the natural language processing model can also be used to process query documents, that is, the same model can be used to process query questions and query documents, and there is no limitation here.

[0098] The data processing method provided in the embodiments of this specification can use a natural language processing model to perform semantic recognition on query questions for different types of query data, and use a document parsing model to perform document parsing on query documents. While improving the efficiency of semantic recognition, it can also improve the accuracy of target query items.

[0099] Step 204: using the large language model, obtaining at least one project query department corresponding to the target query project.

[0100] Among them, the project query department can be understood as the department responsible for evaluating or processing the target query project. In the medical registration scenario, the project query department can be understood as the department, which refers to the department in the hospital or other institutions responsible for specific disciplines or professional fields. The department can provide registration services to conduct inspections of target query projects in the department.

[0101] In actual applications, on the one hand, there are cases where users are not clear about the executable departments corresponding to the target query items. On the other hand, since there are multiple departments that can perform examinations for a target query item, and users lack professional medical knowledge and cannot fully understand the executable departments, they are also confused when choosing a department.

[0102] For example, for a certain target query item, both Department A and Department B can perform examinations on the target query item. However, since the user knows that the target query item examination can be performed in Department A, he is not aware that Department B can also perform the target query item examination. When the user registers, he will choose a doctor in Department A to register. If the number of registered people in Department B is less than the number of registered people in Department A, the user will select an inappropriate department when registering, which will increase the user's medical treatment time and reduce the user experience.

[0103] Specifically, the large language model can be called, the target query item can be input into the large language model, and one or more departments that can provide examinations for the target query item can be determined to solve the user's confusion when choosing a department, provide the user with more choices, and allocate medical resources more effectively.

[0104] Step 206: Determine a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department based on the object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet preset conditions.

[0105] Among them, the object attribute information of the target object can be understood as information that describes the specific attributes of the target object and its related data. For example, the object attribute information includes but is not limited to the identification of the target object, the geographical location of the target object, the historical operation information of the target object, etc.

[0106] The preset condition may be that the project query department can perform the registration operation, for example, being able to perform the registration operation means being in the opening hours and having an idle number source, that is, the preset condition may be that the project query department is in the opening hours and has an idle number source (wherein, each department or doctor usually has a fixed number of numbers for the day's medical services), that is, when any one or more project query departments in at least one project query department can perform the registration operation, the any one or more project query departments are determined as qualified project query departments, that is, the target project query departments.

[0107] Of course, in actual applications, when users query project query departments that can conduct target query project inspections, the purpose is to query project query departments that can conduct target query project inspections, and there is no registration requirement. At this time, the preset conditions can be understood as project query departments that can conduct target query project inspections; specific preset conditions can be set according to actual conditions and are not limited here.

[0108] The target query institution can be understood as a medical institution or medical service center that includes a target project query department and is more closely matched with the target object; the medical institution or medical service center that is more closely matched with the target object can be understood as a medical institution or medical service center that is geographically close to the target object and is convenient for the target object to seek medical treatment, or a medical institution or medical service center that the target object has visited or made appointments with many times.

[0109] In fact, when the department belongs to a medical institution or a medical service center, each project query department is a project query department under the query institution. Therefore, when the target project query department is determined, the medical institution or medical service center that includes the target project query department can be determined based on the relationship between the department and the medical institution or medical service center to which it belongs. For example, Department C and Department D of Hospital H1 are both target project query departments, then Hospital H1 is an institution that includes the target project query department. If Department C of Hospital H2 (the same department can exist in different hospitals) is also a target project query department, then Hospital H2 is also an institution that includes the target project query department.

[0110] The target item query object can be understood as a specific object that a user can register or consult in the target item query department, such as the target item query object is a doctor.

[0111] In actual applications, when users register online, they complete the registration according to the process of selecting a hospital, selecting a department in the hospital, and further selecting a doctor in the department. Usually, when the user wants to conduct an examination of the target query item and the preset condition is that the registration operation can be performed, a reasonable selection of the department is necessary, and there is no high requirement for the specific doctor in the department to conduct the examination. Therefore, the preset condition is set on the selection of the department, that is, the department is the department that meets the preset condition (registration can be performed), and it is not limited whether the doctors in the department have idle numbers. As long as there are doctors with idle numbers in the department, the idle numbers of the department are the sum of the idle numbers of the doctors contained in the department.

[0112] Specifically, a target project query department can be screened out from at least one project query department according to preset conditions, a query agency that includes the target project query department and is more closely matched with the target object can be determined as the target query agency, and the target project query object in the target project query department can be determined.

[0113] In one or more embodiments of the present specification, the initial query organization including the target project query organization can be determined first according to at least one project query organization, and then the initial query organization can be sorted based on the object attribute information of the target object to obtain the target query organization, that is, the initial query organization is determined first, and then the initial query organization is sorted based on the matching degree with the user. The specific implementation is as follows:

[0114] The step of determining a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department comprises:

[0115] Determine an initial query agency according to the at least one project query department, wherein the target project query department is set in the initial query agency;

[0116] Determining the institution priority of the initial query institution according to the object attribute information of the target object;

[0117] According to the institution priorities of the initial query institutions, the initial query institutions are sorted to obtain target query institutions, and the target project query departments in the target query institutions and the target project query objects in the target project query departments are determined.

[0118] Specifically, when the project inquiry department belongs to an inquiry agency, different inquiry agencies may have the same project inquiry department. Therefore, based on at least one project inquiry department, a project inquiry department that meets the preset conditions is determined from the project inquiry departments of the inquiry agencies, that is, the target project inquiry agency, and the inquiry agency including the target project inquiry agency is determined as the initial inquiry agency.

[0119] For example, at least one project query department includes project query departments A, C, and D. When determining the project query department that meets the preset conditions based on at least one project query department, the project query department that meets the preset conditions is determined from the query agency. For example, if hospital H1 includes project query departments C and D that meet the preset conditions, then hospital H1 is the initial query agency. If hospital H2 includes project query department C that meets the preset conditions (that is, different hospitals can have the same department), then hospital H2 is also the initial query agency. At this time, the target project query departments in hospital H1 are project query departments C and D, and the target project query department in hospital H2 is project query department C.

[0120] When the initial query agency is determined, the agency priority of the initial query agency can be determined according to the object attribute information of the target object. Specifically, an evaluation standard for the agency priority can be first formulated. For example, the evaluation standard can include the distance between the agency and the geographical location of the target object, the level of the agency, whether the agency is a designated medical insurance agency, etc.; in the embodiment of the present specification, the initial query agency is prioritized from near to far according to the distance between the target object and the geographical location of the initial query agency, and the priority score can also be increased for the initial query agency that the target object has visited many times (more than 3 times within a week) or has made a historical appointment, so that the agency priority of the initial query agency is determined based on the priority score of the initial query agency, and the initial query agency is sorted according to the agency priority to determine the sorted initial query agency, and the sorted initial query agency is determined as the target query agency, that is, the initial query agency with a higher agency priority is ranked in a front order, so that when the target query agency is displayed on the client, the query agency that is more matched with the target object and convenient for the target object to seek medical treatment is pushed first.

[0121] When determining the target project query department in the target query organization, since there is also a corresponding relationship between the project query department and the project query object (the project query object belongs to the project query department), the project query object contained in the target project query department in the target query organization can be determined as the target project query object.

[0122] Of course, in one or more embodiments of the present specification, the target area within a certain range may be determined first according to the object location information in the object attribute information, and within the target area, regional query agencies that meet the preset conditions are screened out according to at least one project query department, and the regional query agencies are sorted based on the historical agency access information in the object attribute information to obtain the target query agency. The specific implementation is as follows:

[0123] The step of determining a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department comprises:

[0124] Determine a target area according to the object location information in the object attribute information, and determine a regional query agency in the target area according to the at least one project query department, wherein the target project query department is provided in the regional query agency;

[0125] Determining the institution priority of the regional query institution according to the historical institution access information in the object attribute information;

[0126] According to the agency priorities of the regional query agencies, the regional query agencies are sorted to obtain target query agencies, and the target project query departments in the target query agencies and the target project query objects in the target project query departments are determined.

[0127] Specifically, first determine the target area based on the object location information in the object attribute information (such as the current geographical location of the target object), such as an area within 10 kilometers around the current geographical location of the target object as the center. Within this area, based on at least one project query department, screen out target project query departments that meet preset conditions, and determine the query agency that includes the target project query department as the regional query agency.

[0128] According to the historical agency access information in the object attribute information (such as access frequency, historical appointment information, etc.), a priority score is given to each regional query agency to determine the agency priority of the regional query agency, and the regional query agencies are sorted according to their agency priority to obtain the target query agency. In a similar manner to the above, the target project query object in the target project query department is determined.

[0129] The data processing method provided in the embodiments of this specification can first screen out the target project query departments that meet the preset conditions to determine the initial query agency, and then sort the initial query agencies according to the degree of matching with the target object to obtain the target query agency. It can also first circle a target area according to the object attribute information of the target object, thereby improving the screening efficiency when the regional query agency is obtained through screening, and sorting through the regional query agencies to obtain the target query agency. The specific method of obtaining the target query agency is not limited. By obtaining the target query agency, medical resources can be reasonably allocated to avoid the target object from wasting time and energy on unnecessary agencies or departments. When the target query agency meets user needs and is more suitable for users, the conversion rate and user experience can be improved.

[0130] In one or more embodiments of the present specification, the object priority corresponding to the target project query object can also be determined, thereby sorting the target project query objects so that the target objects can directly make an appointment based on the project query object. The specific implementation is as follows:

[0131] After determining the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department, the method further includes:

[0132] Determining the object priority of the target item query object according to the object attribute information of the target object;

[0133] The target item query objects are sorted according to the object priority of the target item query objects to obtain sorted target item query objects, and the sorted target item query objects are determined as recommended item query objects.

[0134] Specifically, when the target object makes an appointment and registers, you can choose a query agency to register. The specific process is to select the query agency, select the project query department in the query agency, and select the project query object in the project query department. You can also directly select the project query object to make an appointment and register. Therefore, when the target project query department is obtained through screening, the target project query objects in the target project query department can also be sorted to determine the recommended project query objects.

[0135] In actual applications, for the target item query object that can be pre-registered, the object priority of the target item query object can be determined according to the (historical reservation information) in the object attribute information, such as the object priority of the target item query object that has been pre-registered in the past is higher than the object priority of the target item query object that has not been pre-registered. Therefore, the target item query objects can be sorted based on the object priority to obtain the sorted target item query objects, and the sorted target item query objects are the recommended item query objects.

[0136] Continuing with the above example, if project query departments C and D in hospital H1 are target project query departments, and project query department C in hospital H2 is the target project query department; when project query department C in hospital H1 includes project query objects f1 and f2, project query department D in hospital H1 includes project query objects f3, f4, and f5, and project query department C in hospital H2 includes project query objects f6 and f7, f1-f7 are determined as target project query objects, and the target project query objects f1-f7 are sorted to obtain recommended project query objects.

[0137] The data processing method provided in the embodiments of this specification can not only obtain the target query agency, but also sort the target project query objects to obtain recommended project query objects, so as to provide the target objects with diversified appointment registration options, that is, not only can the target query agency be selected for appointment registration, but also the recommended project query objects can be selected for appointment registration, thereby meeting the diverse needs of users and improving user experience.

[0138] Step 208: Return the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department to the client.

[0139] By returning the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department to the client, it is convenient to display them to the user in the user interaction interface of the client, so that the user can make a selection conveniently.

[0140] In one or more embodiments of the present specification, when a recommended project query object is obtained, the target query organization, target project query department, target project query object, and recommended project query object can be displayed in the user interaction interface of the client according to a preset display position. The specific implementation is as follows:

[0141] After determining the ranked target item query object as the recommended item query object, the method further includes:

[0142] The recommended item query object is returned to the client, so that the recommended item query object and the target query organization, the target item query department in the target query organization, and the target item query object in the target item query department are displayed on the client according to a preset display position.

[0143] Among them, the preset display position can be set according to actual conditions and is not limited here.

[0144] In actual applications, the target query organization and the recommended project query object can be displayed as two sections in the user interaction interface of the client. The display method of these two sections can be up and down or left and right, and there is no limitation here.

[0145] In the target query organization section, the organization display column of the target query organization is displayed, and the target project query department can be displayed in the organization display column of each target query organization. When the user clicks on the target project query department in the target query organization, the target project query object in the target project query department is displayed. In the recommended project query object section, the object display column of the recommended project query object is displayed, and in the object display column of each recommended project query object, the project query department to which the corresponding project query object belongs can be displayed. The specific display method can be set according to the actual situation and is not limited here.

[0146] The data processing method provided in the embodiments of this specification realizes "one-to-many mapping between examinations and departments" through a large language model, and provides efficient order decision guidance based on the object attribute information and supply information (project query departments with number sources) of the target object, thereby promoting appointment conversion and improving decision-making efficiency. It also effectively allocates medical resources through accurate recommendations on query agencies, project query departments, and project query objects, thereby reducing the waste of time and resources caused by improper user selection.

[0147] See also Figure 3 , Figure 3 A flow chart of a data processing method applied to a client provided by an embodiment of the present specification is shown, which specifically includes the following steps.

[0148] Step 302: Receive query data of the target object, and send an item query instruction of the target object to the server according to the query data.

[0149] The query data may be understood as a query question or a query document, and details may be found in the above implementation examples, which will not be elaborated here.

[0150] According to the received query data of the target object, an item query instruction of the target object is sent to the server. The item instruction may carry the original query data or the target query item obtained after the client recognizes the query data.

[0151] In one or more embodiments of the present specification, the sending of the project query instruction of the target object to the server according to the query data includes:

[0152] Performing semantic recognition on the query data to determine a target query item;

[0153] A project query instruction of the target object is sent to the server according to the target query item, wherein the project query instruction includes project information of the target query item.

[0154] The performing semantic recognition on the query data to determine the target query item includes:

[0155] The query data is input into the large language model, and the large language model is used to perform semantic analysis on the query data to determine the target query item.

[0156] The step of inputting the query data into the large language model, performing semantic analysis on the query data using the large language model, and determining the target query item includes:

[0157] When it is determined that the query data is a query question, a natural language processing model is used to perform semantic recognition on the query question to determine a target query item corresponding to the query question; or

[0158] When it is determined that the query data is a query document, a document parsing model is used to perform semantic recognition on the query document to determine a target query item corresponding to the query document.

[0159] Specifically, the implementation of semantic recognition of query data and determination of target query items on the client is consistent with the implementation of semantic recognition of query data and determination of target query items on the server in the above embodiment, and will not be repeated here.

[0160] Step 304: Receive and display the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server according to the project query instruction, wherein the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are determined by the server according to the above-mentioned data processing method.

[0161] When the client receives the target query agency, the target project query department in the target query agency, and the target project query object in the target project query department returned by the server, the target query agency, the target project query department in the target query agency, and the target project query object in the target project query department are displayed to facilitate the user to make an appointment.

[0162] In one or more embodiments of this specification, when displaying the target query organization, reasonable organization display information that meets user needs can be displayed for the target query organization based on the organization information of the target query organization and the object attribute information of the target object. The specific implementation is as follows:

[0163] The receiving and displaying of the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department, which are returned by the server according to the project query instruction, includes:

[0164] Receiving the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department, which are returned by the server according to the project query instruction;

[0165] According to the organization information of the target query organization and the object attribute information of the target object, obtaining the organization display information corresponding to the target query organization;

[0166] The organization display information corresponding to the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are displayed.

[0167] Among them, the institutional information of the target query institution includes but is not limited to the institutional level (such as A, B), whether it is a designated medical insurance institution, address location and other information, and the object attribute information includes information on whether the target object has ever made an appointment with the target query institution; the institution display information may include the institutional level of the target query institution, whether it is a designated medical insurance institution, whether the target object has ever made an appointment and other information.

[0168] When the institution display information corresponding to the target query institution is obtained based on the institution information of the target query institution and the object attribute information of the target object, the distance between the target query institution and the target object can be calculated based on the geographical location of the target query institution in the institution information and the geographical location in the object attribute information. That is, the institution display information can include not only information such as the institution level of the target query institution, whether it is a designated medical insurance institution, whether the target object has made an appointment, etc., but also the distance between the target query institution and the target object.

[0169] The agency display information corresponding to the target query agency, the target project query department in the target query agency, and the target project query object in the target project query department can be displayed in the client. Of course, in actual applications, when one target query agency corresponds to one agency display column, the agency display information, the target project query department in the target query agency, and the target project query object in the target project query department can be displayed in the agency display column, and the display content in the agency display column can be deleted as appropriate, which is not limited here.

[0170] In addition, in the above embodiment, when the recommended item query object is obtained and returned to the client, the recommended item query object is displayed, for example, each recommended item query object corresponds to an object display column.

[0171] The data processing method provided in the embodiments of this specification can facilitate users to understand the relevant information of the target query agency more clearly by displaying the agency display information corresponding to the target query agency, and provide more references for users to select the target query agency for appointment registration. That is, through rich agency display information of the target query agency, it helps users to better understand the target query agency and the services it provides, thereby improving user satisfaction and trust and promoting appointment conversion rate.

[0172] In one or more embodiments of the present specification, when the client displays the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department, the target object can send a corresponding access request by interacting with these displayed contents, thereby displaying the corresponding access page. The specific implementation is as follows:

[0173] After receiving and displaying the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department, which are returned by the server according to the project query instruction, the method further includes:

[0174] In response to the target object's institution access request for the target query institution, displaying to the target object a department object access page corresponding to the target project query department in the target query institution, wherein the department object access page includes the target project query object in the target project query department; or

[0175] In response to the object access request of the target object for the target project query object, an object access page corresponding to the target project query object is displayed to the target object.

[0176] Among them, the department object access page can be understood as the result page displayed after selecting the target project query department, displaying the object display column corresponding to the target project query object in the target project query department; the object access page can be understood as the result page displayed after selecting the target project query object, displaying the reservable information corresponding to the target project query object (for example, the reservable information is the idle number source information in different time periods), and appointment registration can be realized by clicking on the reservable information.

[0177] In the existing scheme, after the target object clicks on the agency display bar corresponding to the target query agency, he will enter the agency homepage of the target query agency. When he clicks on the appointment registration on the agency homepage, he needs to further select the project query department. In the embodiment of this specification, when the target object clicks on the agency display bar corresponding to the target query agency, an agency access request of the target query agency is sent to the client, and the department object access page corresponding to the target project query department in the target query agency is displayed to the target object accordingly.

[0178] When the target object clicks on the object display bar corresponding to the target project query object, an object access request of the target project query object is sent to the client, and the object access page corresponding to the target project query object is displayed to the target object so that the target object can make an appointment.

[0179] The data processing method provided in the embodiments of this specification can directly enter the department object access page corresponding to the target project query department in the target query agency when the target object clicks on the target query agency, thereby reducing the original link of entering the target query agency homepage and then jumping to the project query department, thereby greatly improving the registration efficiency of the target object.

[0180] In one or more embodiments of this specification, the interaction between the target object and the client is realized based on the user interaction interface of the client, so that the user can operate clearly and efficiently. The specific implementation method is as follows:

[0181] The receiving query data of the target object includes:

[0182] Receiving query data sent by the target object through a user interaction interface;

[0183] The receiving and displaying of the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department, which are returned by the server according to the project query instruction, includes:

[0184] Receive and display to the target object on the user interaction interface the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server according to the project query instruction.

[0185] The data processing method provided in the embodiments of this specification can automatically identify the examination requirements in the natural language input by the user through the semantic understanding of the large language model on the client side, and can also perform document parsing on the user's physical examination report, thereby improving the user experience of the registration service in a variety of ways and providing users with more efficient and convenient registration services.

[0186] See also Figure 4 , Figure 4 A flow chart of a data processing method applied to a data processing system provided in an embodiment of the present specification is shown, which specifically includes the following steps.

[0187] Specifically, the data processing system includes a client and a server.

[0188] Step 402: The client receives query data of the target object, and sends an item query instruction of the target object to the server according to the query data;

[0189] Step 404: the server, in response to the project query instruction of the target object sent by the client, determines the target query project according to the project query instruction, obtains at least one project query department corresponding to the target query project by using a large language model, determines the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet a preset condition, and returns the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department to the client;

[0190] Step 406: The client receives and displays the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server.

[0191] For the specific implementation, please refer to the above embodiments, which will not be described in detail here.

[0192] The data processing method provided in the embodiments of this specification can extract structured information and identify specific examination items when the client receives user input for natural language processing, and use a large language model on the server to implement "one-to-many mapping of examinations and departments", determine at least one project query department, and determine the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department based on the object attribute information of the target object, at least one project query department, and preset conditions, so as to provide efficient order decision guidance and promote appointment conversion.

[0193] See also Figure 5 , Figure 5 A schematic diagram of a user interaction interface provided by an embodiment of this specification is shown.

[0194] Specifically, when the user enters keywords in the search bar on his own, related high-frequency search terms or questions can be linked based on AI capabilities, thereby reducing input costs and improving efficiency and user experience; based on AI semantic recognition technology, by analyzing the user's natural language input, structured information is extracted and specific examination items are identified, and then mapped to multiple departments available for application, using registration supply information (the recommended hospitals are all hospitals with appointment sources in the current supply pool, and such a recommendation strategy can promote actual registration conversion rates) combined with user information (including historical appointment information and geographic location information, etc., giving priority to recommending hospitals where the user has "registered", and users have a stronger sense of trust in such hospitals, and such recommendations are more likely to lead to new conversions; combined with the user's current location coordinates, recommending hospitals that are closer, reducing the user's time cost and increasing the success rate of registration), more suitable hospital departments and doctors are pushed to users, providing users with efficient registration service support; the above-mentioned registration supply information and user information are stored in a database.

[0195] On the client side, Figure 5 The user interaction interface shown can first give the corresponding answer based on the user's natural language input, that is, multiple departments corresponding to the examination items, and then recommend hospitals and doctors to the user based on the departments available for application. The hospital can display the departments related to the search term this time, eliminating interference, and when clicking on the hospital, it will jump directly to the registration page of the corresponding department, which displays the doctors included in the department.

[0196] See also Figure 6 , Figure 6 is another schematic diagram of a user interaction interface provided by an embodiment of this specification;

[0197] The "Interpretation of Physical Examination Report" control is displayed at the bottom of the client user interaction interface (the display position of the control is not limited). When the user clicks the "Interpretation of Physical Examination Report" control, the physical examination report can be submitted and uploaded.

[0198] When a user uploads a physical examination report, the report is analyzed. In actual applications, during the analysis process, in order to provide a better user experience and avoid long periods of silent waiting for the user, simple communication with the user can be increased. For example, AI capabilities can be used to extend some related questions, such as asking the user whether the physical examination report is his or her own, to facilitate subsequent association with file creation.

[0199] After the analysis is completed, the interpretation report can be displayed according to the risk level (such as key concern, priority concern, daily concern), and department guidance can be provided in each concern section. When the user clicks on the department guidance, it jumps to Figure 5 In the interface shown.

[0200] That is, without associating a physical examination report, based on search recommendations, the user inputs natural language, the front end (client) performs natural language processing, extracts structured information and identifies specific examination items, and the back end (server) uses a large language model to achieve "one-to-many mapping between examinations and departments", and provides efficient order decision guidance based on user information and registration information, and the front end presents the recommended results to the user.

[0201] When associating physical examination reports, based on the AI ​​report interpretation guidance, users upload and submit physical examination reports. The front end learns more information through dialogue interaction, and the back end uses a large language model to achieve "one-to-many mapping between examinations and departments". It also provides efficient order decision guidance based on user information and registration information. The front end presents the report interpretation details and recommended departments to users, and users click to jump to the corresponding registration page.

[0202] The data processing method provided in the embodiments of this specification can recommend hospitals and doctors based on user searches, and can also interpret and guide according to uploaded experience reports, provide a variety of recommendation methods, and automatically identify examination requirements in natural language with the help of semantic understanding technology, thereby significantly improving the user experience of registration services. It can also effectively allocate medical resources through accurate department recommendations, reduce time and resource waste caused by improper department selection by users, and optimize resource allocation.

[0203] Corresponding to the above method embodiment, this specification also provides a data processing device embodiment, Figure 7 FIG. 1 is a schematic diagram showing the structure of a data processing device provided by an embodiment of the present specification. Figure 7 As shown, the device comprises:

[0204] The project determination module 702 is configured to respond to the project query instruction of the target object sent by the client and determine the target query project according to the project query instruction;

[0205] The department obtaining module 704 is configured to obtain at least one project query department corresponding to the target query project by using a large language model;

[0206] The target determination module 706 is configured to determine a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet a preset condition;

[0207] The data sending module 708 is configured to return the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department to the client.

[0208] Optionally, the project determination module 702 is further configured to:

[0209] The target query item is determined according to the item information of the target query item carried in the item query instruction.

[0210] Optionally, the project determination module 702 is further configured to:

[0211] The query data of the target object carried in the item query instruction is determined, and semantic recognition is performed on the query data to determine the target query item.

[0212] Optionally, the project determination module 702 is further configured to:

[0213] The query data is input into the large language model, and the large language model is used to perform semantic recognition on the query data to determine the target query item.

[0214] Optionally, the project determination module 702 is further configured to:

[0215] When it is determined that the query data is a query question, a natural language processing model is used to perform semantic recognition on the query question to determine a target query item corresponding to the query question; or

[0216] When it is determined that the query data is a query document, a document parsing model is used to perform semantic recognition on the query document to determine a target query item corresponding to the query document.

[0217] Optionally, the target determination module 706 is further configured to:

[0218] Determine an initial query agency according to the at least one project query department, wherein the target project query department is set in the initial query agency;

[0219] Determining the institution priority of the initial query institution according to the object attribute information of the target object;

[0220] According to the institution priorities of the initial query institutions, the initial query institutions are sorted to obtain target query institutions, and the target project query departments in the target query institutions and the target project query objects in the target project query departments are determined.

[0221] Optionally, the target determination module 706 is further configured to:

[0222] Determine a target area according to the object location information in the object attribute information, and determine a regional query agency in the target area according to the at least one project query department, wherein the target project query department is provided in the regional query agency;

[0223] Determining the institution priority of the regional query institution according to the historical institution access information in the object attribute information;

[0224] According to the agency priorities of the regional query agencies, the regional query agencies are sorted to obtain target query agencies, and the target project query departments in the target query agencies and the target project query objects in the target project query departments are determined.

[0225] The device further comprises:

[0226] The object sorting module is configured to determine the object priority of the target project query object based on the object attribute information of the target object; sort the target project query object according to the object priority of the target project query object, obtain the sorted target project query object, and determine the sorted target project query object as the recommended project query object.

[0227] The device further comprises:

[0228] The data return module is configured to return the recommended project query object to the client, so that the recommended project query object and the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are displayed on the client according to a preset display position.

[0229] The above is a schematic scheme of a data processing device applied to a server in this embodiment. It should be noted that the technical scheme of the data processing device and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the data processing device can be referred to the description of the technical scheme of the above data processing method.

[0230] Corresponding to the above method embodiment, this specification also provides another data processing device embodiment, Figure 8 FIG. 2 shows a schematic diagram of the structure of another data processing device provided by an embodiment of the present specification. Figure 8 As shown, the device comprises:

[0231] The instruction sending module 802 is configured to receive query data of a target object, and send an item query instruction of the target object to the server according to the query data;

[0232] The data receiving module 804 is configured to receive and display the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server according to the project query instruction, wherein the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are determined by the server according to the above-mentioned data processing method.

[0233] Optionally, the instruction sending module 802 is further configured to:

[0234] Performing semantic recognition on the query data to determine a target query item;

[0235] A project query instruction of the target object is sent to the server according to the target query item, wherein the project query instruction includes project information of the target query item.

[0236] Optionally, the instruction sending module 802 is further configured to:

[0237] The query data is input into the large language model, and the large language model is used to perform semantic analysis on the query data to determine the target query item.

[0238] Optionally, the instruction sending module 802 is further configured to:

[0239] When it is determined that the query data is a query question, a natural language processing model is used to perform semantic recognition on the query question to determine a target query item corresponding to the query question; or

[0240] When it is determined that the query data is a query document, a document parsing model is used to perform semantic recognition on the query document to determine a target query item corresponding to the query document.

[0241] Optionally, the data receiving module 804 is further configured to:

[0242] Receiving the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department, which are returned by the server according to the project query instruction;

[0243] According to the organization information of the target query organization and the object attribute information of the target object, obtaining the organization display information corresponding to the target query organization;

[0244] The organization display information corresponding to the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are displayed.

[0245] The device further comprises:

[0246] A response request module is configured to, in response to the target object's institution access request for the target query institution, display to the target object a department object access page corresponding to the target project query department in the target query institution, wherein the department object access page includes the target project query object in the target project query department; or to, in response to the target object's object access request for the target project query object, display to the target object an object access page corresponding to the target project query object.

[0247] Optionally, the instruction sending module 802 is further configured to:

[0248] Receive query data sent by the target object through a user interaction interface.

[0249] Optionally, the data receiving module 804 is further configured to:

[0250] Receive and display to the target object on the user interaction interface the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server according to the project query instruction.

[0251] The above is a schematic scheme of a data processing device applied to a client in this embodiment. It should be noted that the technical scheme of the data processing device and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the data processing device can be referred to the description of the technical scheme of the above data processing method.

[0252] Corresponding to the above method embodiment, this specification also provides a data processing system embodiment, Fig. 9 FIG. 1 shows a schematic diagram of a data processing system provided by an embodiment of the present specification. Fig. 9 As shown, the system includes a client 902 and a server 904, wherein:

[0253] The client 902 is used to receive query data of the target object, and send a project query instruction of the target object to the server 904 according to the query data;

[0254] The server 904 is used to respond to the project query instruction of the target object sent by the client 902, determine the target query project according to the project query instruction, obtain at least one project query department corresponding to the target query project by using a large language model, determine the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet the preset conditions, and return the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department to the client 902;

[0255] The client 902 is used to receive and display the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server 904 .

[0256] The above is a schematic scheme of a data processing system of this embodiment. It should be noted that the technical scheme of the data processing system and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the data processing system can be referred to the description of the technical scheme of the above data processing method.

[0257] Fig.10 A structural block diagram of a computing device 1000 provided according to an embodiment of the present specification is shown.

[0258] The computing device 1000 includes:

[0259] Memory 1010 and processor 1020;

[0260] The memory 1010 is used to store computer programs / instructions, and the processor 1020 is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor 1020, the steps of the data processing method are implemented.

[0261] In one or more embodiments of the present specification, the computing device may be understood as an integrated intelligent terminal, including but not limited to a server, a desktop computer, a PC (Personal Computer), an all-in-one model machine, a mobile phone, a tablet computer or other portable intelligent terminal, etc., and the computing device may be pre-installed with the model described in the above embodiments of the present application.

[0262] Specifically, the computing device can preset multiple types of models, including but not limited to models in the fields of natural language processing, visual processing, speech processing, code processing, multimodal task processing, etc., so as to provide a variety of model choices. In different product forms, the computing device can support one or more model usage methods, including but not limited to model training, model calling, model fine-tuning, model deployment, model reasoning and application, etc. In some product forms, the computing device also supports model management, including but not limited to multi-type model management (supporting the management of multiple types of models such as discriminants and generative models), model version control (supporting the control of different model versions), model evaluation (based on model evaluation tools, evaluating the performance and effect of models), etc. In other product forms, the computing device can also create applications based on models, provide API (Application Programming Interface, application programming interface) calling capabilities, and can call models to the created applications through API interfaces, while providing application management tools to achieve management and monitoring of applications.

[0263] Furthermore, the computing device can also include data management (supporting the creation and management of model tuning data sets), a training center (providing rich training resources to help users learn and master AI (Artificial Intelligence) technology), and basic management and control capabilities (providing enterprise-level basic management and control capabilities to ensure the security and efficient operation of the system). Through the above functions, a comprehensive, integrated AI development, training, deployment and application device is provided.

[0264] In addition, the components of the computing device 1000 include but are not limited to a memory 1010 and a processor 1020. The processor 1020 and the memory 1010 may be connected via a bus.

[0265] The computing device 1000 may also include an access device that enables the computing device 1000 to communicate with a database storing data via one or more networks. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a global microwave interconnection access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0266] In one embodiment of the present specification, the above components of the computing device 1000 and Fig.10 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Fig.10 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0267] The computing device 1000 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 1000 may also be a mobile or stationary server.

[0268] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above data processing method.

[0269] An embodiment of the present specification further provides a computer-readable storage medium storing a computer program / instruction, which implements the steps of the above-mentioned data processing method when executed by a processor.

[0270] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above data processing method.

[0271] An embodiment of the present specification also provides a computer program product, including a computer program / instruction, which implements the steps of the above data processing method when executed by a processor.

[0272] The above is a schematic scheme of a computer program product of this embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the above data processing method belong to the same concept, and the details not described in detail in the technical scheme of the computer program product can be referred to the description of the technical scheme of the above data processing method.

[0273] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0274] The computer program / instruction includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0275] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0276] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0277] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A data processing method, applied to a server, comprising: In response to a project query instruction of a target object sent by a client, determining a target query project according to the project query instruction; Using a large language model, obtaining at least one project query department corresponding to the target query project; Determine a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department, wherein the target project query department is one or more of the at least one project query department that meet a preset condition; The target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are returned to the client.

2. The data processing method according to claim 1, wherein the step of determining a target query organization, a target project query department in the target query organization, and a target project query object in the target project query department based on the object attribute information of the target object and the at least one project query department comprises: Determine an initial query organization according to the at least one project query department, wherein the target project query department is set in the initial query organization; Determining the institution priority of the initial query institution according to the object attribute information of the target object; According to the institution priorities of the initial query institutions, the initial query institutions are sorted to obtain target query institutions, and the target project query departments in the target query institutions and the target project query objects in the target project query departments are determined.

3. The data processing method according to any one of claims 1 to 2, after determining the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department according to the object attribute information of the target object and the at least one project query department, further comprising: Determining the object priority of the target item query object according to the object attribute information of the target object; The target item query objects are sorted according to the object priority of the target item query objects to obtain sorted target item query objects, and the sorted target item query objects are determined as recommended item query objects.

4. The data processing method according to claim 3, after determining the ranked target item query object as the recommended item query object, further comprising: The recommended item query object is returned to the client, so that the recommended item query object and the target query organization, the target item query department in the target query organization, and the target item query object in the target item query department are displayed on the client according to a preset display position.

5. A data processing method, applied to a client, comprising: Receive query data of the target object, and send a project query instruction of the target object to the server according to the query data; Receive and display the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department, returned by the server according to the project query instruction. Among them, the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are determined by the server according to the data processing method according to any one of claims 1-4.

6. The data processing method according to claim 5, wherein the step of sending a query instruction of the target object to the server according to the query data comprises: Performing semantic recognition on the query data to determine a target query item; A project query instruction of the target object is sent to the server according to the target query item, wherein the project query instruction includes project information of the target query item.

7. The data processing method according to claim 6, wherein the performing semantic recognition on the query data to determine the target query item comprises: The query data is input into the large language model, and the large language model is used to perform semantic analysis on the query data to determine the target query item.

8. The data processing method according to claim 7, wherein the inputting the query data into the large language model, performing semantic analysis on the query data using the large language model, and determining the target query item comprises: When it is determined that the query data is a query question, a natural language processing model is used to perform semantic recognition on the query question to determine a target query item corresponding to the query question; or When it is determined that the query data is a query document, a document parsing model is used to perform semantic recognition on the query document to determine a target query item corresponding to the query document.

9. The data processing method according to claim 5, wherein the receiving and displaying of the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server according to the project query instruction comprises: Receiving the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department, which are returned by the server according to the project query instruction; According to the organization information of the target query organization and the object attribute information of the target object, obtaining the organization display information corresponding to the target query organization; The organization display information corresponding to the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department are displayed.

10. The data processing method according to any one of claims 6 to 9, after receiving and displaying the target query organization, the target project query department in the target query organization, and the target project query object in the target project query department returned by the server according to the project query instruction, further comprising: In response to the target object's institution access request for the target query institution, displaying to the target object a department object access page corresponding to the target project query department in the target query institution, wherein the department object access page includes the target project query object in the target project query department; or In response to the object access request of the target object for the target project query object, an object access page corresponding to the target project query object is displayed to the target object.

11. A computing device comprising: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the method described in any one of claims 1 to 10 are implemented.

Images