Smart city rule engine system and method based on large model

Abstract

The embodiment of the invention provides a smart city rule engine system and method based on a large model. The system is applied to the technical field of Internet of Things, comprises a data acquisition receiving port, a character and voice analysis module, an intention instruction recognition module, a rule chain module and a smart city service driving module, and comprises the steps of performing intention recognition processing on character and voice data of a client to obtain an intention recognition result; performing analysis processing on the intention recognition result to obtain an instruction analysis list; an instruction set is combined based on the intention recognition result and the instruction analysis list, and a rule chain conforming to rule engine logic description is generated through the instruction set; and automatically executing the service scene based on the rule chain and the service data. In this way, through the large model technology, the rule chain is automatically generated and optimized, and the service scene is automatically processed through the rule engine, and compared with a traditional rule engine system, the system has higher intellectualization, automation and expansibility.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet of Things technology, and in particular to a smart city rule engine system and method based on a large model. Background Art

[0002] With the advancement of big model technology, big model technology has made continuous innovation and breakthroughs in the application field and has been further applied to all walks of life. At the same time, with the rapid development of the Internet of Things, the Internet of Things technology has also been continuously implemented in the field of smart cities to provide intelligent services. Various Internet of Things devices have been installed in various units of the city such as communities, parks, and streets to serve various business scenarios. The rule engine is the core function of the smart city platform. As an engine for processing various complex business logics, it is equivalent to the brain of the smart city platform. Through the rule engine, the smart city platform can process massive device data and system event data every day, and realize the flexible processing of massive data replication business logic.

[0003] Although the existing IoT platform rule engine can realize business logic processing of up to trillions of massive data, it requires manual configuration of a large number of business rules and business scenarios, and it is difficult to quickly adjust a large number of them during operation. Through the combination of large model technology, the smart city platform can automatically generate various business scenario rules for different spaces, different scenarios, and different urban units, which can reduce a lot of manual operation and maintenance workload, and generate more efficient smart scenario rules through continuous iteration and learning, helping the smart city platform to operate efficiently and achieve the goal of energy saving and efficiency improvement.

[0004] Therefore, there is an urgent need to provide a system and method that can combine big model technology and assist the smart city rule engine. Summary of the invention

[0005] The present disclosure provides a smart city rule engine system and method based on a big model, which at least solves the technical problems of low efficiency and low automation of existing manual configuration of business rules by utilizing the big model technology in combination with the rule engine.

[0006] According to a first aspect of the present disclosure, there is provided a smart city rule engine system based on a large model, comprising: a data collection receiving port, a text and speech analysis module, an intention instruction recognition module, a rule chain module, and a smart city business driving module;

[0007] The data acquisition receiving port is used to receive and store external data information, wherein the external data information includes business data and client text and voice data;

[0008] The text and speech analysis module is used to perform intent recognition processing on the client text and speech data to obtain an intent recognition result;

[0009] The intention instruction recognition module is used to parse the intention recognition result to obtain an instruction parsing list;

[0010] The rule chain module is used to combine an instruction set based on the intention recognition result and the instruction parsing list, and generate a rule chain that conforms to the logic description of the rule engine through the instruction set;

[0011] The smart city business driving module is used to automatically execute business scenarios based on the rule chain and the business data.

[0012] According to the above aspects and any possible implementation, there is further provided an implementation, wherein the data acquisition receiving port includes a business data acquisition module and a client text and voice data acquisition module;

[0013] The business data collection module is used to collect and store business data through various devices running on the smart city platform;

[0014] The client text and voice data acquisition module is used to receive and store the voice and text information of the customer data.

[0015] According to the above aspects and any possible implementation, an implementation is further provided, wherein the text-to-speech analysis module includes a text conversion module, a control instruction recognition module, an offline intention instruction recognition module, an online intention instruction recognition module, and an intention logic generation module;

[0016] The text conversion module is used to convert the voice information into voice text information;

[0017] The control instruction recognition module is used to recognize the instruction keywords in the voice text information and the text information to obtain the instruction keywords;

[0018] The offline intention instruction recognition module is used to obtain keywords in the voice text information in an offline state, and generate corresponding intention answers for publication. If it fails, it will turn to the online intention instruction recognition module:

[0019] The online intention command recognition module is used to crawl relevant information in the client voice data from the network using crawler technology, obtain the intention command recognition result by expanding the search scope, and generate the corresponding intention answer for publication;

[0020] The intention logic generation module is used to construct a logical relationship between keywords based on the directive keywords and the intention answers.

[0021] According to the above aspects and any possible implementation, an implementation is further provided, wherein the recognition process of the intention instruction recognition module is:

[0022] An initialization module loads an instruction knowledge base into a local memory and splits the instruction knowledge base into separate words;

[0023] Deconstructing and splitting the command keywords and the intended answers, and obtaining the standard command words with the highest similarity to the structured words in the command knowledge base by word matching;

[0024] An instruction parsing list is generated according to the standard instruction words and the logical relationship, wherein the instruction parsing list is a specific API corresponding to the system.

[0025] According to the above aspects and any possible implementation, there is further provided an implementation, wherein the rule chain module includes a rule chain generation module, a rule engine module and a rule chain management module;

[0026] The rule chain generation module is used to construct a rule chain based on the intention recognition result and the instruction parsing list;

[0027] The rule engine module is used to drive the rule chain to automatically execute and complete the business scenario according to the business data;

[0028] The rule chain management module is used to edit, modify or delete the rule chain.

[0029] According to the above aspects and any possible implementation, there is further provided an implementation, wherein the rule chain includes a message, a rule node, and an associated chain;

[0030] The message is used to receive information from the text and speech analysis module and the intention instruction recognition module:

[0031] The rule node is used to process the message and trigger the execution of the rule chain;

[0032] The association chain is used to associate messages. The association chain receives an outbound message from a previous rule node and forwards the message to different next nodes according to the specific content of the outbound message.

[0033] According to the above aspects and any possible implementation, there is further provided an implementation, wherein the rule node includes a check node, an enrichment node, a transformation node, and a behavior node;

[0034] The rule node filters, transforms and executes the message, calls the API of each smart city business, and completes the business scenario execution.

[0035] According to the aspects described above and any possible implementation method, an implementation method is further provided, wherein the system also includes a domain big model module, and the domain big model module is used to generate a docking domain big model and an instruction parsing big model and transmit them to the intention instruction recognition module for intention instruction recognition, generate a rule chain content domain big model and transmit it to the rule chain module for rule chain generation.

[0036] According to a second aspect of the present disclosure, a smart city rule engine method based on a big model is provided, which is implemented using the smart city rule engine system based on a big model as described in the first aspect, and includes the following steps:

[0037] Receiving and storing external data information, wherein the external data information includes business data and client text and voice data;

[0038] Performing intent recognition processing on the client text and voice data to obtain an intent recognition result;

[0039] Parsing the intention recognition result to obtain an instruction parsing list;

[0040] Combining an instruction set based on the intention recognition result and the instruction parsing list, and generating a rule chain that conforms to the logic description of the rule engine through the instruction set;

[0041] A business scenario is automatically executed based on the rule chain and the business data.

[0042] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described in the second aspect is implemented.

[0043] Compared with the prior art, the present invention has the following technical effects:

[0044] The big model-based smart city rule engine system and method disclosed in the present invention mainly utilizes big model technology combined with rule engine to realize intelligent and automatic processing of business scenarios in the smart city platform, and drives various business management, business operation and business event handling of the smart city by collecting and receiving various multi-source data such as various Internet of Things devices, business events of smart city platform operation, system notifications and alarms. Through big model technology, rule chains are automatically generated and optimized, and business scenarios are automatically processed through rule engines. Compared with traditional rule engine systems, it has stronger intelligence, automation and scalability.

[0045] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0047] Figure 1 A schematic diagram of the structure of a smart city rule engine system based on a large model according to an embodiment of the present disclosure is shown;

[0048] Figure 2 A schematic diagram of the structure of a data collection receiving port of a smart city rule engine system based on a large model according to an embodiment of the present disclosure is shown;

[0049] Figure 3 A schematic diagram of the structure of a text and speech analysis module of a smart city rule engine system based on a large model according to an embodiment of the present disclosure is shown;

[0050] Figure 4 A schematic diagram of the structure of a rule chain module of a smart city rule engine system based on a large model according to an embodiment of the present disclosure is shown;

[0051] Figure 5 A schematic diagram of a process in a smart city rule engine method based on a large model according to an embodiment of the present disclosure is shown;

[0052] Figure 6 A block diagram of an exemplary electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0055] Reference Figure 1As shown, this embodiment provides a smart city rule engine system based on a large model, including: a data collection receiving port 1, a text and speech analysis module 2, an intention instruction recognition module 3, a rule chain module 4 and a smart city business driving module 5;

[0056] The data acquisition receiving port 1 is used to receive and store external data information, wherein the external data information includes business data and client text and voice data;

[0057] The text and speech analysis module 2 is used to perform intention recognition processing on the client text and speech data to obtain the intention recognition result;

[0058] The intention instruction recognition module 3 is used to parse the intention recognition result to obtain an instruction parsing list;

[0059] The rule chain module 4 is used to combine the instruction set based on the intention recognition result and the instruction parsing list, and generate a rule chain that conforms to the logic description of the rule engine through the instruction set;

[0060] The smart city business driver module 5 is used to automatically execute business scenarios based on rule chains and business data. The smart city business driver module 5 drives specific business operations. Through the rule chain drive, the rule node calls the API of each smart city business to complete the automatic operation of the business scenario. For example, before going to work, the relevant equipment is automatically turned on. When the equipment fails, a work order is automatically generated to notify the operation and maintenance personnel. When a group incident occurs in a certain space, the relevant smart city platform operation and maintenance personnel are notified in time to intervene in time.

[0061] Furthermore, in this example, Figure 2 As shown, the data acquisition receiving port 1 includes a business data acquisition module 11 and a client text and voice data acquisition module 12;

[0062] The business data collection module 11 is used to collect and store business data through various devices running on the smart city platform;

[0063] The client text and voice data collection module 12 is used to receive and store the voice and text information of the customer data.

[0064] In this embodiment, the data acquisition receiving port 1 is responsible for connecting all data of the smart city platform, including device data, system data, and third-party data, and pushes them to the rule engine module through the message middleware through the message channel. Device data includes device operation data and device event reporting data, system data includes system operation and system notification alarms, and third-party data includes third-party event data, third-party analysis data and other data. This module collects the above data and pushes it to the rule chain module 4 through the message middleware. By receiving various devices and business data running on the smart city platform, the rule engine is triggered, and the rule chain that complies with the rules is triggered by the data, automatically driving the business scenario operation of the smart city.

[0065] Furthermore, in this embodiment, if Figure 3 As shown, the text and speech analysis module 2 includes a text conversion module 21, a control instruction recognition module 22, an offline intention instruction recognition module 23, an online intention instruction recognition module 24 and an intention logic generation module 25;

[0066] The text conversion module 21 is used to convert the voice information into voice text information;

[0067] The control instruction recognition module 22 is used to recognize the instruction keywords in the voice text information and the text information to obtain the instruction keywords;

[0068] The offline intention instruction recognition module 23 is used to obtain keywords in the voice text information in an offline state, and generate corresponding intention answers for publication. If it fails, it will turn to the online intention instruction recognition module 24;

[0069] The online intention instruction recognition module 24 is used to crawl relevant information in the client voice data from the network using crawler technology, obtain the intention instruction recognition result by expanding the search scope, and generate the corresponding intention answer for publication;

[0070] The intention logic generation module 25 is used to construct the logical relationship between keywords based on the directive keywords and the intended answers.

[0071] Furthermore, in the present embodiment, the recognition process of the intended instruction recognition module 3 is as follows: initializing the module, loading the instruction knowledge base into the local memory, and splitting the instruction knowledge base into separate words; performing word deconstruction and splitting on the instruction keywords and intended answers, and obtaining the standard instruction words with the highest similarity to the structured words in the instruction knowledge base through word matching; generating an instruction parsing list based on the standard instruction words and logical relationships, wherein the instruction parsing list is the specific API corresponding to the system.

[0072] In this embodiment, through the intent content and intent analysis, the domain model parses out the instruction list corresponding to the intent. The instructions in the instruction list are the specific APIs corresponding to the system functions. The API can execute specific instructions in the smart city platform to complete the system function call.

[0073] Furthermore, in this embodiment, if Figure 4 As shown, the rule chain module 4 includes a rule chain generation module 41, a rule engine module 42 and a rule chain management module 43. In this embodiment, the rule chain is highly customizable, and the user can freely define multiple rule chains to handle different data processing requirements.

[0074] The rule chain generation module 41 is used to construct a rule chain based on the intent recognition results and the instruction parsing list; the rule engine module 42 is used to drive the rule chain to automatically execute and complete the business scenario; the rule chain management module 43 manages the generated rule chain through the rule chain management module, and is responsible for editing, modifying, and deleting the rule chain data, and also viewing and manually adding rule chains in the visual interface.

[0075] The rule chain module 4 analyzes the intent content and the instruction content, combines the intent logic and sequence, and combines the instruction set to generate a rule chain that conforms to the logic description of the rule engine through the instruction set. The generated rule chain is pushed to the rule chain management module. The rule chain is responsible for specific business logic processing and is composed of specific processing units. The core of the processing unit is a specific instruction.

[0076] In this embodiment, the rule chain includes a message, a rule node, and an association chain.

[0077] The message is used to receive the information transmitted from the text and speech analysis module 2 and the intention command recognition module 3; the rule node is used to process the message and trigger the execution of the rule chain; the association chain is used to associate the message. The association chain receives the outbound message of the previous rule node and forwards the message to different next nodes according to the specific content of the outbound message.

[0078] Rule nodes include check nodes, enrichment nodes, transformation nodes, and behavior nodes; rule nodes filter, transform, and execute messages, call the APIs of various smart city businesses, and complete business scenario execution.

[0079] Each rule chain in the rule engine will form a workflow framework with specific logic to monitor and save messages. When abnormal data is found, feedback will be given according to the specified logic, such as pushing alarm information or printing logs. At present, there is a mature practice framework for rule chains based on event streams, and the rule chain nodes are highly operable. These advantages provide feasibility for rule chain-based data fusion methods.

[0080] Furthermore, in this embodiment, the smart city rule engine system based on the big model also includes a domain big model module 6, which is used to generate a docking domain big model and an instruction parsing big model and transmit them to the intention instruction recognition module 3 for intention instruction recognition, generate a rule chain content domain big model and transmit it to the rule chain module 4 for rule chain generation.

[0081] The domain big model module 6 is responsible for the domain big model of instruction parsing, intent recognition, and rule chain content generation. At the same time, it receives historical rule chain training sample materials for training and learning to improve the accuracy of rule chain generation.

[0082] like Figure 5 As shown, this embodiment also provides a smart city rule engine method based on a big model, which is implemented using the smart city rule engine system based on a big model as described in the above embodiment, and includes the following steps:

[0083] S101, receiving and storing external data information, wherein the external data information includes business data and client text and voice data;

[0084] S102, performing intent recognition processing on the client text and voice data to obtain an intent recognition result;

[0085] S103, parsing the intent recognition result to obtain an instruction parsing list;

[0086] S104, combining an instruction set based on the intention recognition result and the instruction parsing list, and generating a rule chain that conforms to the logic description of the rule engine through the instruction set;

[0087] S105. Automatically execute business scenarios based on rule chains and business data.

[0088] In this embodiment, the user inputs a description of the intelligent scenario to be processed, automatically generates a rule chain for the scheduled task, and triggers it regularly through the rule engine to complete the execution of the business scenario.

[0089] Specific examples are as follows:

[0090] System operation example 1

[0091] The user inputs the description of the intelligent scenario that needs to be processed, automatically generates a rule chain for the scheduled task, and triggers it regularly through the rule engine to complete the execution of the business scenario.

[0092] Input: Work Purpose Help me open the sunshades when it rains, and turn on the air conditioner if the temperature is low.

[0093] Intent recognition: working day, judging the weather, opening curtains, judging documents, turning on the air conditioner.

[0094] Command recognition: scheduled tasks, working day judgment API, weather judgment API, curtain opening API, temperature judgment API, air conditioning turning on API.

[0095] Generate a rule chain: set the time at 8 am every day → determine whether it is a working day → determine whether the temperature is less than or lower than 16℃ → if yes, open the curtains and turn on the air conditioner.

[0096] Rule chain management: Generate a rule chain for a scheduled task.

[0097] Rule engine: The rule chain is scheduled to run at 8 a.m. every day and executed according to the chain logic.

[0098] System operation example 2

[0099] The corresponding processing rule chain is generated through user input content. If the system collects or receives fighting event data, the rule chain is triggered and the business logic of the rule chain is executed according to the generated logic.

[0100] Input: If a fight is detected, send a system alarm and phone notification.

[0101] Intent recognition: fighting, system alarm, and phone calls.

[0102] Command recognition: fighting incidents, generating system alarms, calling phone APIs.

[0103] Generate a rule chain: receive a fight event → generate a system alarm → call the person in charge and call up the video from the camera where the fight originated.

[0104] Rule chain management: Generate a rule chain.

[0105] Rule engine: If the rule engine receives fighting event data, it executes the rule chain.

[0106] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of each step described above can refer to the corresponding process in the aforementioned system embodiment and will not be repeated here.

[0107] Figure 6A schematic block diagram of an electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0108] The electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a ROM 302 or a computer program loaded from a storage unit 308 into a RAM 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0109] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0110] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the smart city rule engine method based on a large model. For example, in some embodiments, the smart city rule engine method based on a large model may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the smart city rule engine method based on a large model described above may be executed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute the big model-based smart city rule engine method in any other appropriate manner (for example, by means of firmware).

[0111] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0113] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0115] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0116] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0117] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0118] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A smart city rule engine system based on a large model, characterized in that: include: Data collection receiving port (1), text and speech analysis module (2), intention and instruction recognition module (3), rule chain module (4) and smart city business driving module (5); The data acquisition receiving port (1) is used to receive and store external data information, wherein the external data information includes business data and client text and voice data; The text and speech analysis module (2) is used to perform intention recognition processing on the client text and speech data to obtain an intention recognition result; The intention instruction recognition module (3) is used to parse the intention recognition result to obtain an instruction parsing list; The rule chain module (4) is used to combine an instruction set based on the intention recognition result and the instruction parsing list, and generate a rule chain that conforms to the logic description of the rule engine through the instruction set; The smart city business driving module (5) is used to automatically execute business scenarios based on the rule chain and the business data.

2. The smart city rule engine system based on a large model according to claim 1 is characterized in that: The data acquisition receiving port (1) comprises a business data acquisition module (11) and a client text and voice data acquisition module (12); The business data collection module (11) is used to collect and store business data through various devices running on the smart city platform; The client text and voice data acquisition module (12) is used to receive and store the voice and text information of the customer data.

3. The smart city rule engine system based on a large model according to claim 1 is characterized in that: The text-speech analysis module (2) comprises a text conversion module (21), a control instruction recognition module (22), an offline intention instruction recognition module (23), an online intention instruction recognition module (24) and an intention logic generation module (25); The text conversion module (21) is used to convert the voice information into voice text information; The control instruction recognition module (22) is used to recognize instruction keywords in the voice text information and text information to obtain instruction keywords; The offline intention instruction recognition module (23) is used to obtain keywords in the voice text information in an offline state, and generate corresponding intention answers for publication. If it fails, it will turn to the online intention instruction recognition module (24); The online intention instruction recognition module (24) is used to crawl relevant information in the client voice data from the network using crawler technology, obtain the intention instruction recognition result by expanding the search range, and generate a corresponding intention answer for publication; The intention logic generation module (25) is used to construct a logical relationship between keywords based on the directive keywords and the intention answers.

4. The smart city rule engine system based on a large model according to claim 3 is characterized in that: The recognition process of the intention instruction recognition module (3) is as follows: An initialization module loads an instruction knowledge base into a local memory and splits the instruction knowledge base into separate words; Deconstructing and splitting the command keywords and the intended answers, and obtaining the standard command words with the highest similarity to the structured words in the command knowledge base by word matching; An instruction parsing list is generated according to the standard instruction words and the logical relationship, wherein the instruction parsing list is a specific API corresponding to the system.

5. The smart city rule engine system based on a large model according to claim 1 is characterized in that: The rule chain module (4) comprises a rule chain generation module (41), a rule engine module (42) and a rule chain management module (43); The rule chain generation module (41) is used to construct a rule chain based on the intention recognition result and the instruction parsing list; The rule engine module (42) is used to drive the rule chain to automatically execute and complete the business scenario according to the business data; The rule chain management module (43) is used to edit, modify or delete the rule chain.

6. The big model-based smart city rule engine system according to claim 5 is characterized in that: The rule chain includes messages, rule nodes and associated chains; The message is used to receive information transmitted from the text and speech analysis module (2) and the intention instruction recognition module (3); The rule node is used to process the message and trigger the execution of the rule chain; The association chain is used to associate messages. The association chain receives an outbound message from a previous rule node and forwards the message to different next nodes according to the specific content of the outbound message.

7. The big model-based smart city rule engine system according to claim 6, characterized in that: The rule nodes include check nodes, enrichment nodes, transformation nodes and behavior nodes; The rule node filters, transforms and executes the message, calls the API of each smart city business, and completes the business scenario execution.

8. The big model-based smart city rule engine system according to claim 1 is characterized in that: The system also includes a domain big model module (6), which is used to generate a docking domain big model and an instruction parsing big model and transmit them to the intention instruction recognition module (3) for intention instruction recognition, generate a rule chain content domain big model and transmit it to the rule chain module (4) for rule chain generation.

9. A smart city rule engine method based on a large model, characterized in that: The method is implemented by using a smart city rule engine system based on a large model as described in any one of claims 1 to 8, characterized in that it includes the following steps: Receiving and storing external data information, wherein the external data information includes business data and client text and voice data; Performing intent recognition processing on the client text and voice data to obtain an intent recognition result; Parsing the intention recognition result to obtain an instruction parsing list; Combining an instruction set based on the intention recognition result and the instruction parsing list, and generating a rule chain that conforms to the logic description of the rule engine through the instruction set; A business scenario is automatically executed based on the rule chain and the business data.

10. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of claim 9.

Images