Function identifier sorting method and device based on exhibition tool, equipment and medium

Abstract

The embodiment of the invention provides a function identifier sorting method and device based on an exhibition tool, equipment and a medium, and belongs to the technical field of financial science and technology. The method comprises the steps of obtaining business attribute data, target object attribute data, target object position data and historical identification operation data of a target object; retrieving based on the target object position data and the business attribute data to obtain retrieval object data; performing identifier sorting on the candidate function identifiers based on the target object position data, the retrieval object position data and the retrieval object type to obtain an initial identifier list; performing retrieval enhancement on the initial large language model based on the historical identification operation data and the target object attribute data to obtain a target large language model; and according to the target large language model, carrying out identification sorting on the retrieval object attribute data and the initial identification list to obtain a target identification list. According to the embodiment of the invention, the sorting accuracy of the function identifiers corresponding to the business modules in the page of the exhibition tool can be improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a method, device, equipment, and medium for sorting functional identifiers based on business development tools. Background Art

[0002] Business development tools are tools that help insurance agents, brokers and other professionals improve efficiency, expand business scope and enhance customer satisfaction during business development. Currently, on the page of mobile business development tools used by sales personnel, the function logos of multiple business modules of various business lines can be displayed, and each function logo corresponds to a module node in the business process, and users can enter the corresponding lower-level menu or function page by clicking on the function logo. In this way, this function logo provides the function of accessing the corresponding business module, allowing professionals to easily obtain and use the required resources.

[0003] Related technology in clients with business development tools usually sorts the function identifiers of business modules according to the frequency of historical operation behaviors of the operating object, that is, the function identifiers of business modules that have been used more frequently in history are placed in front, and the function identifiers of business modules that have been used less frequently are placed in the back. However, this method only sorts according to the number of user operations, which can easily affect the accuracy of the function identifier sorting due to erroneous clicks by the operating object, thereby affecting the efficiency of the operating object in conducting business based on the business development tool. Therefore, how to improve the accuracy of sorting the function identifiers corresponding to the business modules in the page of the business development tool has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose an entry sorting method and device, equipment, and storage medium based on a business development tool, aiming to improve the sorting accuracy of function identifiers corresponding to business modules in the page of the business development tool.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a method for sorting function identifiers based on a business development tool, the method comprising:

[0006] Acquire the business attribute data, target object attribute data, target object location data and historical identification operation data of the target object; wherein the business attribute data is used to characterize the attribute data related to the management business of the target object, the target object location data is used to indicate the current location of the target object, and the historical identification operation data is used to indicate the historical operation of the target object on the function identification in the target business exhibition page;

[0007] Performing object retrieval based on the target object location data and the service attribute data to obtain retrieval object data of the retrieval object; wherein the retrieval object data includes detection object location data, retrieval object type and retrieval object attribute data, the detection object location data is used to indicate the current location of the retrieval object, and the retrieval object type is used to indicate the relationship between the service node of the retrieval object and the management service;

[0008] Acquire a candidate function identifier based on the business attribute data;

[0009] Sort the candidate function identifiers based on the target object location data, the search object location data and the search object type to obtain an initial identifier list;

[0010] Performing retrieval enhancement on a pre-trained initial large language model based on the historical identification operation data and the target object attribute data to obtain a target large language model;

[0011] The retrieval object attribute data and the initial identification list are sorted according to the target large language model to obtain a target identification list, and the target identification list is used to update the identification list in the target business exhibition page.

[0012] In some embodiments, performing object retrieval based on the target object location data and the business attribute data to obtain retrieval object data of the retrieval object includes:

[0013] Performing object matching based on the target object position data and a preset search distance to determine a candidate object; wherein the distance between the candidate object and the target object is less than or equal to the preset search distance;

[0014] Screening the candidate objects based on the business attribute data to determine the search object;

[0015] Acquire the search object data of the search object.

[0016] In some embodiments, the business attribute data includes pending business processes and completed business processes; and the object screening of the candidate objects based on the business attribute data to determine the search object includes:

[0017] Acquire a candidate business type of the candidate object, where the candidate business type is used to indicate a relationship between a business node of the candidate object and the management business, and the candidate business type includes a first business type and a second business type, where the first business type is used to characterize that the business node of the candidate object is in the pending business process corresponding to the management business, and the second business type is used to characterize that the business node of the candidate object is in the completed business process corresponding to the management business;

[0018] Selecting the candidate objects based on the first business type to obtain the search object;

[0019] Counting the operation function identifiers of the searched objects to obtain the number of object function identifiers;

[0020] If the number of the object function identifiers is less than a preset number, object selection is performed on the candidate objects based on the second business type to obtain the search object.

[0021] In some embodiments, the step of sorting the candidate function identifiers based on the target object location data, the search object location data, and the search object type to obtain an initial identifier list includes:

[0022] Obtaining a process weight of the candidate function identifier in the corresponding object process;

[0023] Determining a type weight of the candidate function identifier based on the search object type;

[0024] Performing distance calculation on the target object position data and the initial object position data to obtain an object distance;

[0025] determining a distance weight of the candidate function identifier based on the object distance;

[0026] Performing weighted calculation on the type weight, the distance weight and the process weight to obtain an identification weight of the candidate function identification;

[0027] The candidate function identifiers are sorted based on the identifier weights to obtain the initial identifier list.

[0028] In some embodiments, the acquiring of the target object's business attribute data, target object attribute data, target object location data, and historical identification operation data includes:

[0029] Acquire the usage status of the target object on the target business development page; the usage status includes a busy status, and the busy status is used to indicate that the list in the target business development page is updated;

[0030] If the usage status is the busy status, generating a function identification sorting signal for the target business exhibition page;

[0031] The business attribute data, target object attribute data, target object location data and historical identification operation data of the target object are acquired based on the function identification sorting signal.

[0032] In some embodiments, obtaining the usage status of the target object on the target business development page includes:

[0033] When a signal triggered by the target object to enter the target business page is identified, determining that the target object's use status of the target business page is the busy status; or

[0034] When it is identified that the target object has not triggered an operation on at least one function identifier in the target business development page within a first preset time interval before the current time, the use state is determined to be the busy state; or,

[0035] When it is identified that the continuous stay time of the target object on the target business exhibition page is less than or equal to the second preset time interval, the usage status is determined to be the busy status; wherein the first preset time interval is greater than the second preset time interval.

[0036] In some embodiments, the method further comprises:

[0037] Obtaining the number of logo displays on the target business exhibition page;

[0038] The target identification list is selected based on the identification display quantity to obtain an identification display list and a hidden identification list.

[0039] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a function identification sorting device based on a business development tool, the device comprising:

[0040] A first acquisition module is used to acquire business attribute data, target object attribute data, target object location data and historical identification operation data of a target object; wherein the business attribute data is used to characterize attribute data related to the management business of the target object, the target object location data is used to indicate the current location of the target object, and the historical identification operation data is used to indicate the historical operation of the target object on the function identification in the target business exhibition page;

[0041] A retrieval module, configured to perform an object retrieval based on the target object location data and the service attribute data to obtain retrieval object data of the retrieval object; wherein the retrieval object data includes detection object location data, retrieval object type and retrieval object attribute data, the detection object location data is used to indicate the current location of the retrieval object, and the retrieval object type is used to indicate the relationship between the service node of the retrieval object and the management service;

[0042] A second acquisition module, used to acquire a candidate function identifier based on the business attribute data;

[0043] A first sorting module, configured to sort the candidate function identifiers based on the target object location data, the search object location data and the search object type to obtain an initial identifier list;

[0044] A retrieval enhancement module, configured to perform retrieval enhancement on a pre-trained initial large language model based on the historical identification operation data and the target object attribute data to obtain a target large language model;

[0045] The second sorting module is used to sort the retrieval object attribute data and the initial identification list according to the target large language model to obtain a target identification list, and the target identification list is used to update the identification list in the target business exhibition page.

[0046] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the function identification sorting method based on business development tools described in the first aspect.

[0047] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the function identification sorting method based on business development tools described in the first aspect above.

[0048] The present application proposes a method, device, equipment, and medium for sorting functional identifiers based on business development tools, which obtains business attribute data, target object attribute data, target object location data, and historical identification operation data of a target object, wherein the business attribute data is used to characterize attribute data related to the management business of the target object, the target object location data is used to indicate the current location of the target object, and the historical identification operation data is used to indicate the target object's historical operations on the functional identifiers in the target business development page; further, based on the target object location data and the business attribute data, an object retrieval is performed to obtain retrieval object data of the retrieval object, and the retrieval object data includes detection object location data, retrieval object type, and retrieval object attribute data , the detection object location data is used to indicate the current location of the retrieval object, and the retrieval object type is used to indicate the relationship between the service node of the retrieval object and the management business; further, based on the business attribute data, the candidate function identifiers are obtained, and the candidate function identifiers are sorted based on the target object location data, the retrieval object location data and the retrieval object type to obtain an initial identifier list; further, based on the historical identifier operation data and the target object attribute data, the pre-trained initial large language model is retrieved and enhanced to obtain a target large language model; according to the target large language model, the retrieval object attribute data and the initial identifier list are sorted to obtain a target identifier list, and the target identifier list is used to update the identifier list in the target business exhibition page. The embodiment of the present application can first perform object retrieval based on the object location data and the business attribute data to obtain the retrieval object related to the management business of the target object, and then further sort the candidate function identifier and the target large language model related to the management business of the target object twice based on the relevant data of the retrieval object to obtain a target identifier list for updating the target business exhibition page of the target object. Therefore, compared with the related art that only sorts the function identifiers in the business development page according to the number of user operations, the present application sorts the function identifiers twice in combination with geographic location and large language model, which can effectively improve the sorting accuracy of the function identifiers corresponding to the business modules in the business development tool page. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of a method for sorting function identifiers based on business development tools provided in an embodiment of the present application;

[0050] Figure 2 yes Figure 1 A flowchart of step S110 in FIG.

[0051] Figure 3 yes Figure 1 A flowchart of step S120 in FIG.

[0052] Figure 4 yes Figure 3 A flowchart of step S330 in FIG.

[0053] Figure 5 yes Figure 1 A flowchart of step S140 in FIG.

[0054] Figure 6 It is a page schematic diagram of a target business development page provided in an embodiment of the present application;

[0055] Figure 7 is another flow chart of the method for sorting function identifiers based on business development tools provided in an embodiment of the present application;

[0056] Figure 8 It is a structural diagram of a function identification sorting device based on a business development tool provided in an embodiment of the present application;

[0057] Fig. 9 It is a hardware structure diagram of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0061] First, some nouns involved in this application are analyzed:

[0062] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0063] Natural language processing (NLP): NLP uses computers to process, understand and apply human languages ​​(such as Chinese and English). NLP is a branch of artificial intelligence and an interdisciplinary subject between computer science and linguistics. It is often referred to as computational linguistics. Natural language processing includes grammatical analysis, semantic analysis, and text understanding. Natural language processing is often used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information intent recognition, information extraction and filtering, text classification and clustering, public opinion analysis and opinion mining. It involves data mining related to language processing, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research, and linguistic research related to language computing.

[0064] Large Language Models (LLMs): A language model based on deep learning and natural language processing techniques. The pre-trained large language model is applied to a specific task or data set, and the model parameters are adjusted through supervised learning to adapt to the requirements of the specific task. The core of LLMs is the use of deep learning methods, which are usually based on the Transformer architecture and can capture the complexity and diversity of language. LLMs are usually composed of multi-layer neural networks that can learn and model the input text data and then generate output with logical coherence.

[0065] Location-based services (LBS) are services that use wireless communication networks (or satellite positioning systems) through mobile terminals. They use various types of positioning technologies to obtain the current location of the positioning device and provide information resources and basic services to the positioning device through the mobile Internet.

[0066] Retrieval Augmented Generation (RAG): is an advanced method that combines information retrieval technology and large language models (LLMs). RAG can enhance the ability of LLMs by leveraging external knowledge bases, enabling them to generate more accurate and relevant text content. The RAG workflow usually includes three key steps: retrieving relevant information (i.e., RAG first retrieves information related to the user query from a wide range of document databases), using this information to guide text generation, and generating the final text output (i.e., RAG generates natural and fluent text based on context and grammatical rules).

[0067] Business development tools are tools that help insurance agents, brokers and other professionals improve efficiency, expand business scope and enhance customer satisfaction in the process of business development. At present, the pages of mobile business development tools used by sales personnel involve various business modules of many business lines, that is, the page can display the function identifiers corresponding to various business modules of various business lines, and each function identifier is equivalent to an entry control, which is used to correspond to a module node in the business process, and the user can enter the corresponding lower menu or function page by clicking the function identifier. In this way, this function identifier provides the function of accessing the corresponding business module, so that professionals can easily obtain and use the required resources. For example, in the sales scenario in the field of financial technology, this business module can include marketing center, business opportunity filling, material submission, video review, electronic signing, contract inquiry, order management, residual value assessment, etc., covering each node entrance in the entire business process.

[0068] Related technology In the client with business development tools, the list in the business development page can be set for single-point custom sorting such as system default during development, system single preset, or manual secondary sorting, so as to realize the sorting of the function identifiers corresponding to such business modules. However, in actual customer service, it is usually necessary to review the required business modules in combination with many factors such as customer categories, business lines, and progress nodes, and click on the function identifier to enter, which is time-consuming and very unfavorable for offline rapid business development. In addition, according to the survey and combined with experience, the related technology usually adopts the following method for the client with the function identifier sorting of the business development business module such as APP or mini program used by the account manager for business development: adaptive sorting according to the historical operation behavior of the account manager, that is, the modules that have been used more in history are ranked in front, and the modules that have been used less will be ranked behind. In addition, the function of sorting and searching is provided at the system level, that is, a search or custom sorting entrance is provided, so that the account manager can search for business modules to access. In addition, a quick entrance can be set above the sorting of the business development module, and then the screening part is formed into an additional entrance list displayed at the top of the page. That is to say, the list in the business development page can sort the function identifiers of the business modules according to the frequency of the historical operation behaviors of the operation objects, that is, the function identifiers of the business modules that have been used more frequently in history are placed in front, and the function identifiers of the business modules that have been used less frequently are placed in the back.

[0069] However, this method only sorts according to the number of user operations, which can easily affect the accuracy of the function identification sorting due to wrong clicks by the operation object, thereby affecting the efficiency of the operation object in conducting business based on the business development tool.

[0070] Adaptive sorting cannot prioritize based on the latest business forms and regional customer characteristics. For example, if the business development page contains three business modules, the first two of which are upstream in the funnel (the funnel refers to the business conversion link. For example, to buy a product, you need to view the product first, then add it to the shopping cart, and finally submit the order and pay. The upstream here refers to the node that is relatively advanced for some process nodes. For example, for payment, adding a shopping cart is the upstream node), then it must be displayed in the front, but it is very likely that customers who are doing business in this area at the same time will need to use the third business module, so the adaptive sorting is inaccurate. Therefore, how to improve the sorting accuracy of the function identifiers corresponding to the business modules in the business development tool page has become a technical problem that needs to be solved urgently.

[0071] Based on this, the embodiments of the present application provide a method and apparatus, device, and medium for sorting function identifiers based on business development tools, aiming to improve the accuracy of audio feature extraction, thereby improving the accuracy of music sorting.

[0072] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0073] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0074] The method for sorting function identifiers based on business development tools provided in the embodiments of the present application relates to the field of artificial intelligence technology. The method for sorting function identifiers based on business development tools provided in the embodiments of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content De l ivery Network, CDN) and big data and artificial intelligence platforms; the software can be an application that implements the method for sorting function identifiers based on business development tools, etc., but is not limited to the above forms.

[0075] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0076] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to the identity or characteristics of the object, such as object attribute data, object location data, and object operation data, the permission or consent of the object will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain sensitive personal information of the object, the separate permission or separate consent of the object will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the separate permission or separate consent of the object, the necessary object-related data for enabling the normal operation of the embodiment of the present application will be obtained.

[0077] See also Figure 1 , Figure 1 is an optional flow chart of a method for sorting function identifiers based on business development tools provided in an embodiment of the present application. In some embodiments, Figure 1 The method may include but is not limited to steps S110 to S160:

[0078] Step S110, acquiring business attribute data, target object attribute data, target object location data and historical identification operation data of the target object;

[0079] Step S120, performing object retrieval based on the target object location data and the business attribute data to obtain retrieval object data of the retrieval object;

[0080] Step S130, obtaining a candidate function identifier based on the business attribute data;

[0081] Step S140, sorting the candidate function identifiers based on the target object location data, the search object location data and the search object type to obtain an initial identifier list;

[0082] Step S150, performing retrieval enhancement on the pre-trained initial large language model based on the historical identification operation data and the target object attribute data to obtain a target large language model;

[0083] Step S160 , sorting the object attribute data and the initial identification list according to the target large language model to obtain a target identification list.

[0084] In the steps S110 to S160 shown in the embodiment of the present application, the embodiment of the present application can first perform object retrieval based on the object location data and business attribute data to obtain the retrieval object related to the management business of the target object, and then further sort the candidate function identifiers and the target large language model related to the management business of the target object based on the relevant data of the retrieval object twice to obtain a target identifier list for updating the target business page of the target object. Therefore, compared with the related technology that only sorts the function identifiers in the business page according to the number of user operations, the present application combines the geographic location and the large language model to sort the function identifiers twice, which can effectively improve the sorting accuracy of the function identifiers corresponding to the business modules in the page of the business tool.

[0085] In step S110 of some embodiments, business attribute data is used to characterize attribute data related to the management business of the target object. For example, in a sales scenario, business attribute data may reflect the business line that the target object is responsible for. Target object location data is used to indicate the current location of the target object. Historical identification operation data is used to indicate the target object's historical operations on the function identifiers in the target business exhibition page. For example, the target business exhibition page includes five function identifiers, namely function identifier F ID1, function identifier F ID2, function identifier F ID3, function identifier F ID4 and function identifier F ID5, and each function identifier is a business entry corresponding to a business module. The historical identification operation data may indicate that the operations of the target object when processing management business are function identifier F ID3, function identifier F ID2 and function identifier F ID4, respectively.

[0086] It should be noted that the functional identifiers included in the management business may include marketing center, business opportunity filling, material submission, video interview, electronic signing, contract inquiry, order management, residual value assessment, etc., which can cover various business nodes in the entire management business process.

[0087] In some embodiments, see Figure 2 , Figure 2 This is an optional flowchart of step S110 provided in an embodiment of the present application. Wherein, step S110 may specifically include but is not limited to steps S210 to S230:

[0088] Step S210, obtaining the usage status of the target object on the target business exhibition page;

[0089] Step S220: if the usage status is busy, generating a function identification sorting signal for the target business exhibition page;

[0090] Step S230: acquiring the business attribute data, target object attribute data, target object location data and historical identification operation data of the target object based on the function identification sorting signal.

[0091] In step S210 of some embodiments, the target object's usage status of the target business page is used to characterize the target object's recent usage of the target business page. The usage status includes a busy state and a non-busy state, wherein the busy state is used to characterize the update of the list in the target business page, that is, it can characterize that the target object meets the requirement to update the display list in the target business page, and the non-busy state is used to characterize that the list in the target business page is not updated. In other words, the non-busy state refers to the concept that the target object is on a busy line, that is, it is not busy using the function, and updating the list will affect the previous operation of the target object.

[0092] It should be noted that by judging the usage status of the target object for the target business exhibition page, it can be determined whether the target business exhibition page of the target object needs to be updated to avoid erroneous updates, and by correctly updating, the most appropriate function identifier can be displayed for the target object to improve the object experience.

[0093] In some embodiments, obtaining the usage status of the target object for the target business development page may specifically include the following situations:

[0094] When a signal triggering the target object to enter the target business page is identified, it is determined that the target object's use status of the target business page is busy; or,

[0095] When it is identified that the target object has not triggered an operation on at least one function identifier in the target business development page within a first preset time interval before the current time, the use state is determined to be a busy state; or,

[0096] When it is identified that the continuous stay time of the target object on the target business exhibition page is less than or equal to the second preset time interval, the usage status is determined to be a busy state; wherein the first preset time interval is greater than the second preset time interval.

[0097] It should be noted that when the target object triggers the signal to enter the target business exhibition page, it means that the target object has just entered the target display page, which means that at this time, dynamic effects can be used to adjust the display order and content of the function logos in the page.

[0098] It should be noted that the target object has not triggered an operation on at least one function identifier in the target business development page within the first preset time interval before the current time, which means whether the target object has used the function in the target business development page within the most recent first preset time interval based on the current time. For example, the first preset time interval is 30 minutes. When the target object has used the business development tool within the last 30 minutes, that is, has performed operations on the target business development page of the business development tool, it can be determined that the use status is not busy, and the list in the target business development page is not updated to avoid affecting the normal operation of the customer. On the contrary, when the target object has not used the business development tool within the last 30 minutes, it can be determined that the use status is busy, and the list in the target business development page can be updated to provide a more suitable list for the target object.

[0099] It should be noted that the continuous stay time of the target object on the target business page is less than or equal to the second preset time interval, which means whether the continuous stay time of the target object on the target business page is less than or equal to the second preset time interval based on the current time, and the first preset time interval is greater than the second preset time interval. For example, the first preset time interval is 30 minutes, and the second preset time interval is 5 minutes. At this time, based on the current time, if the continuous stay time of the target object on the target business page is greater than 5 minutes, it can be determined that the use status is not busy, and the list in the target business page is not updated to avoid affecting the normal operation of the customer; on the contrary, if the continuous stay time of the target object on the target business page is less than or equal to 5 minutes, it can be determined that the use status is busy, and the list in the target business page is updated.

[0100] Further, in some implementations, when the cumulative stay time of the target object on the target business page within the third preset time interval is greater than the second preset time interval, the use state is determined to be a non-busy state, and the list on the target business page is not updated to avoid affecting the normal operation of the customer, wherein the third preset time interval is greater than the second preset time interval. For example, the third preset time interval is 10 minutes, and the second preset time interval is 5 minutes. At this time, if the cumulative stay time of the target object on the target business page within the last 10 minutes exceeds 5 minutes, the use state is determined to be a non-busy state; conversely, if the cumulative stay time of the target object on the target business page within the last 10 minutes is less than or equal to 5 minutes, the use state is determined to be a busy state.

[0101] In other embodiments, the present application can respond to the operations of the target object in real time when adjusting the list displayed in the target display page. For example, when the target object's finger rests on a certain function point or several function points (i.e., the function identifier of the present application), its sorting is retained and not updated to avoid affecting the normal operation of the account manager.

[0102] In the above embodiment, the present application can more flexibly and dynamically adjust the display list of the target display page by introducing different scenarios for determining the busy state or the non-busy state. In addition, combined with the more accurate sorting method of the present application, the function identifier list corresponding to the qualified business exhibition module can be better included in the dynamic update queue in sequence.

[0103] In step S220 of some embodiments, if the usage status is a busy status, a function identifier sorting signal for the target business exhibition page is generated, and the function identifier sorting signal for the target business exhibition page is used to trigger an update of a display list of the target business exhibition page.

[0104] In step S230 of some embodiments, after obtaining the function identification sorting signal, the business attribute data, target object attribute data, target object location data and historical identification operation data of the target object can be obtained to determine the identification list used to update the target business development page.

[0105] In step S120 of some embodiments, in the first sorting, the present application may first perform an object search based on the target object location data and the business attribute data to obtain the search object data of the search object. That is to say, the present application may first identify nearby objects in combination with the location information. Since offline business objects are distributed in various regions, they have different identities and attributes. In the daily business development process, business objects may include potential customers, pre-sales customers, after-sales customers, non-business customers, etc., and customers in different regions have the use requirements of corresponding business modules. When the mobile office equipment such as mobile phones and computers carried by the target object (such as an account manager) moves to a different region from before, the geographical location latitude and longitude information will change. At this time, the system will automatically identify nearby customers and give priority to finding corresponding business objects according to the business line that the account manager is responsible for. Among them, the search object is an object related to the management business of the target object identified according to the geographical location. The search object data includes detection object location data, search object type and search object attribute data. The detection object location data is used to indicate the current location of the search object, and the search object type is used to indicate the relationship between the business node of the search object and the management business.

[0106] It should be noted that the search objects may include potential objects, pre-sales objects, after-sales objects, non-business objects, etc. Pre-sales objects refer to objects that have made their intentions clear and are in the business process of managing the business but have not yet completed all procedures; after-sales objects refer to objects that have completed all relevant procedures for managing the business; potential objects refer to objects that have not made their intentions clear but have the hope of handling management business; non-business objects refer to objects that have not made their intentions clear and may not necessarily have the hope of handling management business.

[0107] In some embodiments, see Figure 3, Figure 3 This is an optional flow chart of step S120 provided in the embodiment of the present application. Wherein, step S120 may specifically include but is not limited to steps S310 to S330:

[0108] Step S310, performing object matching based on the target object location data and a preset search distance to determine a candidate object;

[0109] Step S320, screening candidate objects based on the business attribute data to determine the search object;

[0110] Step S330, obtaining the search object data of the search object.

[0111] In step S310 of some embodiments, the preset search distance refers to the range distance for searching nearby objects, that is, the target object location data can be used as the center of the circle and the preset search distance can be used as the radius to match nearby objects and determine multiple candidate objects, wherein the distance between the candidate object and the target object is less than or equal to the preset search distance.

[0112] In step S320 and step S330 of some embodiments, the candidate objects are further screened based on the business attribute data to determine the retrieval object, where the retrieval object refers to an object that is more closely associated with the management business of the target object, and retrieval object data of the retrieval object is further obtained.

[0113] When determining the search object, this application will perform a comprehensive screening based on the identity characteristics, business preferences, and geographical distance of nearby objects. The screening action will exclude the part that exceeds the threshold, that is, first screen based on distance, and then combine business attributes and object attributes for further matching. In this way, more effective search objects can be selected, and the sorting accuracy of the function identifiers corresponding to the business modules in the page of the business development tool can be improved.

[0114] It should be noted that the business attribute data includes pending business processes and completed business processes. The pending business processes are used to correspond to pre-sales objects, and the completed business processes are used to correspond to after-sales objects.

[0115] In some embodiments, see Figure 4 , Figure 4 This is an optional flow chart of step S330 provided in the embodiment of the present application. Wherein, step S330 may specifically include but is not limited to steps S410 to S440:

[0116] Step S410, obtaining candidate business types of candidate objects;

[0117] Step S420, selecting candidate objects based on the first business type to obtain search objects;

[0118] Step S430, counting the operation function identifiers of the searched objects to obtain the number of object function identifiers;

[0119] Step S440: If the number of object function identifiers is less than a preset number, object selection is performed on candidate objects based on the second business type to obtain a search object.

[0120] In steps S410 to S430 of some embodiments, the candidate business type is used to indicate the relationship between the business node of the candidate object and the management business, and the candidate business type includes a first business type and a second business type. The first business type is used to characterize that the business node of the candidate object is in a pending business process corresponding to the management business, and the second business type is used to characterize that the business node of the candidate object is in a completed business process corresponding to the management business. After determining the candidate business type of each candidate object, the candidate object of the first business type can be selected as the retrieval object first. Furthermore, the operation function identifiers of the retrieval object are counted to obtain the number of object function identifiers, that is, the number of function identifiers contained in the candidate object of the first business type currently selected is determined, and the number of object function identifiers refers to the number of function identifiers after deduplication, so as to avoid the influence of repeated function identifiers on the identifier sorting.

[0121] In step S440 of some embodiments, if the number of object function identifiers is less than the preset number, object selection is performed on the candidate objects based on the second business type to obtain the search object. The preset number refers to the minimum number of identifier sorting by the large language model or the number of display identifiers specified in the target display page. If the number of object function identifiers determined from the candidate objects of the first business type is less than the preset number, objects can be selected from the candidate objects of the second business type as search objects to update the number of object function identifiers. Furthermore, if the number of updated object function identifiers is still less than the preset number, potential objects and non-business objects can be further selected as new search objects until the number of object function identifiers is equal to the preset number. In other words, when the business processes required by the candidate objects corresponding to the first business type and the second business type cannot form a list of entries with the specified number on the workbench homepage, the application can introduce entry statistics for potential objects and non-business objects.

[0122] In step S130 of some embodiments, before sorting, the present application may obtain candidate function identifiers based on business attribute data. That is to say, a business scenario contains many function identifiers, but only some of them may be related to the management business of the target object. At this time, the candidate function identifiers related to the management business can be obtained according to the business attribute data to avoid the impact of sorting all function identifiers on efficiency. For example, if object A is a new customer, then when handling the business, the function identifiers in its target display page may include new customer entry, real-name authentication, material upload, etc. After object A completes the new customer entry, after real-time update, the function identifiers in the target display page at this time may include electronic signing, contract inquiry, order management, etc., excluding the relevant information of the new customer entry.

[0123] In step S140 of some embodiments, after the candidate function identifiers are determined, the candidate function identifiers can be sorted based on the target object location data, the search object location data and the search object type to obtain an initial identifier list, that is, the first sorting of the function identifiers is achieved in combination with the location distance.

[0124] In some embodiments, see Figure 5 , Figure 5 This is an optional flow chart of step S140 provided in the embodiment of the present application. Wherein, step S140 may specifically include but is not limited to steps S510 to S560:

[0125] Step S510, obtaining the process weight of the candidate function identifier in the corresponding object process;

[0126] Step S520, determining the type weight of the candidate function identifier based on the search object type;

[0127] Step S530, performing distance calculation on the target object position data and the initial object position data to obtain the object distance;

[0128] Step S540, determining the distance weight of the candidate function identifier based on the object distance;

[0129] Step S550, performing weighted calculation on the type weight, the distance weight and the process weight to obtain the identification weight of the candidate function identification;

[0130] Step S560: sorting the candidate function identifiers based on the identifier weights to obtain an initial identifier list.

[0131] In step S510 of some embodiments, in the first sorting, the present application may first obtain the process weight of the candidate function identifier in the object process of multiple search objects. For example, a corresponding weight may be assigned to the function identifier contained in each search object in the process. Then, the process weight of the candidate function identifier may be the average of the process sub-weights of the corresponding candidate function identifiers in the multiple search objects.

[0132] In step S520 of some embodiments, the search object types of the present application include pre-sale objects, after-sale objects, potential objects and non-business objects, and the present application can determine the type weight of the corresponding candidate function identifier according to the search object types in the obtained search objects. Specifically, the usage of the pre-sale object has a greater impact on the sorting result, and a greater weight can be assigned to it; the usage of the non-business object has a smaller impact on the sorting result, and a smaller weight can be assigned to it.

[0133] In step S530 and step S540 of some embodiments, the distance calculation is performed on the target object position data and the initial object position data to obtain the object distance, and the distance weight of the candidate function identifier is determined based on the object distance. For example, when the object distance is small, it means that the usage of the search object corresponding to the initial object position data has a greater impact on the sorting result, and a larger weight can be assigned to it.

[0134] In step S550 of some embodiments, further, the type weight, distance weight and process weight can be weightedly calculated to obtain the identification weight of the candidate function identification, which is used to characterize the weight of the candidate function identification after comprehensive consideration of the retrieval object type, the importance of the identification in the process and the distance.

[0135] In step S560 of some embodiments, the candidate function identifiers are further sorted based on the identifier weights, that is, the function identifiers in the retrieval object process can be sorted from high to low according to the identifier weights, and some candidate function identifiers with the lowest weights are eliminated to obtain an initial identifier list.

[0136] In step S150 of some embodiments, before performing the second sorting, the present application can perform retrieval enhancement on the pre-trained initial large language model based on the historical identification operation data and the target object attribute data to obtain the target large language model. In other words, the present application can use the historical identification operation data and the target object attribute data as RAG information to first train the initial large language model, which is equivalent to letting the initial large language model first learn how to operate in history, which can effectively improve the sorting accuracy of the target large language model.

[0137] In step S160 of some embodiments, when performing the second sorting, the present application may input the retrieval object attribute data and the initial identification list into the target large language model for identification sorting to obtain a target identification list, which is used to update the identification list in the target business exhibition page. Among them, the present application will also simultaneously input the prompt text into the target large language model to sort the function identifications included in the initial identification list, and the target identification list is used to update the identification list in the target business exhibition page.

[0138] It should be noted that this application optimizes the large prediction model based on RAG. Specifically, before answering questions or generating text, the large model first retrieves information from the document and uses the retrieved information to generate content, which can improve the prediction quality. In addition, the large language model mainly consists of three steps: Indexing: The document is divided into blocks, encoded into vectors, and stored in the vector database; Retrieval: Retrieve the top k blocks most relevant to the question based on semantic similarity; Generation: Input the original question and the retrieved word blocks into the large language model together to generate the final answer.

[0139] In the above embodiments, the present application can combine working rules and business rules, introduce historical identification operation data and target object attribute data as RAG information and supplementary prompt text into the target large language model judgment, thereby improving the sorting accuracy of function identifiers corresponding to business modules in the pages of business development tools, and can update the weighted list content and sorting in real time.

[0140] See also Figure 6 , Figure 6 6 is a page schematic diagram of a target business development page provided by an embodiment of the present application. Among them, the target display page 600 includes a first display area 610 for displaying a target identification list, a second display area 620 for displaying a hidden identification list, and a quick search area 630. Since the number of function identifiers included in the target identification list may be greater than the number of function identifiers that can be displayed in the first display area 610, at this time, the excess function identifiers can be placed in the second display area 620 to facilitate the target object to be quickly called. For example, the function identifiers included in the target identification list are sorted from high to low according to the weight: marketing center, business opportunity filling, material submission, video face-to-face review, electronic signing, contract inquiry, order management, residual value assessment, etc., and the number of function identifiers that can be displayed in the first display area 610 is 4. At this time, the marketing center, business opportunity filling, material submission, and video face-to-face review can be displayed in the first display area 610, and electronic signing, contract inquiry, order management, residual value assessment, etc. can be displayed in the second display area 620.

[0141] It should be noted that the Figure 6It is only a schematic diagram of a page of the target business exhibition page, and the specific arrangement format of the target business exhibition page can be flexibly adjusted according to actual needs, and is not specifically limited here.

[0142] In some embodiments, see Figure 7 , Figure 7 This is another optional flow chart of the method for sorting function identifiers based on business development tools provided in an embodiment of the present application. After step S160, the method for sorting function identifiers based on business development tools of the present application may further include steps S710 to S720:

[0143] Step S710, obtaining the number of logo displays of the target business exhibition page;

[0144] Step S720: select the target identifier list based on the identifier display quantity to obtain an identifier display list and a hidden identifier list.

[0145] In steps S710 to S720 of some embodiments, the number of logo displays refers to the number of function logos that can be displayed at one time in the target business exhibition page. Figure 6 As shown, if the number of displayed identifiers is less than the function identifiers included in the target identifier list, the number of displayed identifiers function identifiers can be first obtained according to the order in the target identifier list to obtain the displayed identifier list, and then the hidden identifier list can be obtained based on the remaining function identifiers.

[0146] The embodiment of the present application provides a method for sorting function identifiers based on business development tools. The method can first perform object retrieval based on object location data and business attribute data to obtain retrieval objects related to the management business of the target object, and then further sort the candidate function identifiers and target large language models related to the management business of the target object based on the relevant data of the retrieval object twice to obtain a target identifier list for updating the target business development page of the target object. Since the sorting and search functions of related technologies require the target object to be familiar with the name description and other contents of the business development module, when the memory is not deep, the module is frequently adjusted, or there are multiple modules with the same name, etc., it is not possible to search quickly and obtain search results. The present application can combine LBS, customer data, large language model, etc. to comprehensively judge the priority of the use of the function identification tool of the target object, and intelligently adjust the order of function identifiers. Specifically, the present application can automatically determine the attributes of the customer group according to the visited area, without the need for target object identification, that is, without user triggering, and the system actively updates in real time; part of the content is calculated autonomously by the user device (that is, the first sorting involving the geographic location), and part of the derivative content is distributedly calculated by the server-side large model service; and, through real-time dynamic intelligent adjustment of the order of function identifiers (that is, business module entrances), that is, dialogues based on attributes rather than user input, without the need for retrieval objects or target object dialogues, but completely relying on various types of existing data; in addition, by introducing a large language model to further optimize the statistical results of big data, to make up for the problem of judgment jitter when customer group characteristics are missing, that is, by increasing keyword weights and using a large model for comprehensive judgment, judgment jitter can be reduced. Therefore, the present application combines geographic location and a large language model to sort the function identifiers twice, which can effectively improve the accuracy of sorting the function identifiers corresponding to the business modules in the pages of the business development tools.

[0147] See also Figure 8 The embodiment of the present application further provides a function identification sorting device based on a business development tool, which can implement the function identification sorting method based on a business development tool, and the device includes:

[0148] The first acquisition module 810 is used to acquire business attribute data, target object attribute data, target object location data and historical identification operation data of the target object; wherein the business attribute data is used to characterize attribute data related to the management business of the target object, the target object location data is used to indicate the current location of the target object, and the historical identification operation data is used to indicate the historical operation of the target object on the function identification in the target business exhibition page;

[0149] A retrieval module 820 is used to perform an object search based on the target object location data and the service attribute data to obtain the search object data of the search object; wherein the search object data includes the detection object location data, the search object type and the search object attribute data, the detection object location data is used to indicate the current location of the search object, and the search object type is used to indicate the relationship between the service node of the search object and the management service;

[0150] A second acquisition module 830, used to acquire a candidate function identifier based on the business attribute data;

[0151] A first sorting module 840 is used to sort the candidate function identifiers based on the target object location data, the search object location data and the search object type to obtain an initial identifier list;

[0152] A retrieval enhancement module 850 is used to perform retrieval enhancement on the pre-trained initial large language model based on the historical identification operation data and the target object attribute data to obtain a target large language model;

[0153] The second sorting module 860 is used to sort the object attribute data and the initial identification list according to the target large language model to obtain a target identification list, and the target identification list is used to update the identification list in the target business exhibition page.

[0154] The specific implementation of the function identification sorting device based on the business development tool is basically the same as the specific implementation of the function identification sorting method based on the business development tool mentioned above, and will not be repeated here.

[0155] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned function identification sorting method based on business development tools when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0156] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0157] The processor 910 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0158] The memory 920 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 920 can store an operating system and other applications. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 920, and the processor 910 calls and executes the function identification sorting method based on the business development tool in the embodiment of this application;

[0159] Input / output interface 930, used to implement information input and output;

[0160] Communication interface 940, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WI FI, Bluetooth, etc.);

[0161] bus 950 , which transmits information between the various components of the device (e.g., processor 910 , memory 920 , input / output interface 930 , and communication interface 940 );

[0162] The processor 910 , the memory 920 , the input / output interface 930 , and the communication interface 940 are connected to each other in communication within the device via a bus 950 .

[0163] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned function identification sorting method based on business development tools.

[0164] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0165] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0166] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0167] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0169] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0170] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0171] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0172] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0173] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0174] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0175] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for sorting function identifiers based on business development tools, characterized in that: The method comprises: Acquire the business attribute data, target object attribute data, target object location data and historical identification operation data of the target object; wherein the business attribute data is used to characterize the attribute data related to the management business of the target object, the target object location data is used to indicate the current location of the target object, and the historical identification operation data is used to indicate the historical operation of the target object on the function identification in the target business exhibition page; Performing object retrieval based on the target object location data and the service attribute data to obtain retrieval object data of the retrieval object; wherein the retrieval object data includes detection object location data, retrieval object type and retrieval object attribute data, the detection object location data is used to indicate the current location of the retrieval object, and the retrieval object type is used to indicate the relationship between the service node of the retrieval object and the management service; Acquire a candidate function identifier based on the business attribute data; Sort the candidate function identifiers based on the target object location data, the search object location data and the search object type to obtain an initial identifier list; Performing retrieval enhancement on a pre-trained initial large language model based on the historical identification operation data and the target object attribute data to obtain a target large language model; The retrieval object attribute data and the initial identification list are sorted according to the target large language model to obtain a target identification list, and the target identification list is used to update the identification list in the target business exhibition page.

2. The method according to claim 1, characterized in that The object retrieval based on the target object location data and the business attribute data to obtain the retrieval object data includes: Performing object matching based on the target object position data and a preset search distance to determine a candidate object; wherein the distance between the candidate object and the target object is less than or equal to the preset search distance; Screening the candidate objects based on the business attribute data to determine the search object; Acquire the search object data of the search object.

3. The method according to claim 2, characterized in that The business attribute data includes pending business processes and completed business processes; the object screening of the candidate objects based on the business attribute data to determine the search object includes: Acquire a candidate business type of the candidate object, where the candidate business type is used to indicate a relationship between a business node of the candidate object and the management business, and the candidate business type includes a first business type and a second business type, where the first business type is used to characterize that the business node of the candidate object is in the pending business process corresponding to the management business, and the second business type is used to characterize that the business node of the candidate object is in the completed business process corresponding to the management business; Selecting the candidate objects based on the first business type to obtain the search object; Counting the operation function identifiers of the searched objects to obtain the number of object function identifiers; If the number of the object function identifiers is less than a preset number, object selection is performed on the candidate objects based on the second business type to obtain the search object.

4. The method according to claim 1, characterized in that: The step of sorting the candidate function identifiers based on the target object location data, the search object location data and the search object type to obtain an initial identifier list includes: Obtaining a process weight of the candidate function identifier in the corresponding object process; Determining a type weight of the candidate function identifier based on the search object type; Performing distance calculation on the target object position data and the initial object position data to obtain an object distance; determining a distance weight of the candidate function identifier based on the object distance; Performing weighted calculation on the type weight, the distance weight and the process weight to obtain an identification weight of the candidate function identification; The candidate function identifiers are sorted based on the identifier weights to obtain the initial identifier list.

5. The method according to claim 1, characterized in that The step of obtaining the target object's business attribute data, target object attribute data, target object location data, and historical identification operation data includes: Acquire the usage status of the target object on the target business development page; the usage status includes a busy status, and the busy status is used to indicate that the list in the target business development page is updated; If the usage status is the busy status, generating a function identification sorting signal for the target business exhibition page; The business attribute data, target object attribute data, target object location data and historical identification operation data of the target object are acquired based on the function identification sorting signal.

6. The method according to claim 5, characterized in that The obtaining of the usage status of the target object on the target business development page includes: When a signal triggered by the target object to enter the target business page is identified, determining that the target object's use status of the target business page is the busy status; or When it is identified that the target object has not triggered an operation on at least one function identifier in the target business development page within a first preset time interval before the current time, the use state is determined to be the busy state; or, When it is identified that the continuous stay time of the target object on the target business exhibition page is less than or equal to the second preset time interval, the usage status is determined to be the busy status; wherein the first preset time interval is greater than the second preset time interval.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Obtaining the number of logo displays on the target business exhibition page; The target identification list is selected based on the identification display quantity to obtain an identification display list and a hidden identification list.

8. A function identification sorting device based on business development tools, characterized in that: The device comprises: A first acquisition module is used to acquire business attribute data, target object attribute data, target object location data and historical identification operation data of a target object; wherein the business attribute data is used to characterize attribute data related to the management business of the target object, the target object location data is used to indicate the current location of the target object, and the historical identification operation data is used to indicate the historical operation of the target object on the function identification in the target business exhibition page; A retrieval module, configured to perform an object retrieval based on the target object location data and the service attribute data to obtain retrieval object data of the retrieval object; wherein the retrieval object data includes detection object location data, retrieval object type and retrieval object attribute data, the detection object location data is used to indicate the current location of the retrieval object, and the retrieval object type is used to indicate the relationship between the service node of the retrieval object and the management service; A second acquisition module, used to acquire a candidate function identifier based on the business attribute data; A first sorting module, configured to sort the candidate function identifiers based on the target object location data, the search object location data and the search object type to obtain an initial identifier list; A retrieval enhancement module, configured to perform retrieval enhancement on a pre-trained initial large language model based on the historical identification operation data and the target object attribute data to obtain a target large language model; The second sorting module is used to sort the retrieval object attribute data and the initial identification list according to the target large language model to obtain a target identification list, and the target identification list is used to update the identification list in the target business exhibition page.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images