Property service method and device based on artificial intelligence technology

Abstract

The invention discloses a property service method and device based on an artificial intelligence technology, and the method and device are used for achieving the automatic property service, and the method comprises the steps: receiving consultation information, determining a service type corresponding to the consultation information through a pre-built language model, and determining the keyword information in the consultation information; calling a corresponding business sub-model from a pre-established service model according to the service type; analyzing the keyword information by utilizing the business sub-model so as to determine a corresponding service process; according to the system and the method, the artificial intelligence technology is combined, the consultation information of the user is analyzed and classified, and various property services are completed in a targeted manner in a classified manner, so that the service efficiency and the stability of the service quality are improved, the automatic property services are realized, and the degree of dependence on manpower is reduced.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly to a property service method and device based on artificial intelligence technology. Background Art

[0002] At present, property services in communities often involve property staff directly providing services to owners, that is, traditional manual services. There are various types of property services, and service personnel usually have their own specific responsibilities. For example, it can include transactional services (such as fee payment and handling various procedures), functional services (such as construction and maintenance), parking management, and various daily affairs in the community, etc.

[0003] In reality, such a service method mainly relying on manpower may be inefficient, and the service quality is not stable. In addition, the number of service personnel is limited, and it is usually difficult to be proficient in cross-category service content. Therefore, many times, the problems of owners cannot be solved in the first place.

[0004] That is to say, in the prior art, there is a lack of a property service method that does not rely on or reduces the reliance on manpower, and automated property services cannot be achieved. Summary of the Invention

[0005] The present invention provides a property service method and device based on artificial intelligence technology to achieve automated property services.

[0006] In a first aspect, the present invention provides a property service method based on artificial intelligence technology, including:

[0007] Receiving consultation information, using a pre-established language model to determine the service category corresponding to the consultation information, and determining the keyword information in the consultation information;

[0008] According to the service category, calling a corresponding business sub-model from a pre-established service model;

[0009] Using the business sub-model to analyze the keyword information to determine the corresponding service process;

[0010] Executing the service process.

[0011] Preferably, it further includes:

[0012] Performing data training based on historical property consultation data to establish the language model.

[0013] Preferably, it further includes:

[0014] Performing data training based on historical service data of specific categories to establish the business sub-model;

[0015] The service model is established by using at least one of the business sub-models.

[0016] Preferably, determining the service category corresponding to the consultation information by using a pre-established language model, and determining the keyword information in the consultation information includes:

[0017] Performing semantic analysis on the consultation information to determine the service demands included in the consultation information;

[0018] Determining the service category according to the service demands; the service category includes transaction services, function services, and query services;

[0019] Determining the keyword information in the service demands; the keyword information includes keyword fields and key data.

[0020] Preferably, the business sub-models include a transaction sub-model, a function sub-model, and a query sub-model; using the business sub-models to analyze the keyword information to determine the corresponding service process includes:

[0021] Using the keyword fields to determine a service template;

[0022] Using the service template and according to the key data, determining the service process.

[0023] Preferably, when the service category is a transaction service or a function service, then determining the service process includes:

[0024] Determining a to-be-executed plan, the to-be-executed plan includes execution time information, execution location information, execution personnel information, execution tool information, and / or execution program information.

[0025] Preferably, when the service category is a query service, then determining the service process includes:

[0026] Determining feedback information.

[0027] In a second aspect, the present invention provides a property service device based on artificial intelligence technology, including:

[0028] A semantic analysis module, configured to receive consultation information, determine the service category corresponding to the consultation information by using a pre-established language model, and determine the keyword information in the consultation information;

[0029] A service classification module, configured to call a corresponding business sub-model from a pre-established service model according to the service category;

[0030] A process determination module, configured to use the business sub-model to analyze the keyword information to determine the corresponding service process;

[0031] A service execution module for executing the service process.

[0032] In a third aspect, the present invention provides a readable medium including execution instructions. When a processor of an electronic device executes the execution instructions, the electronic device executes the method described in any one of the first aspect.

[0033] In a fourth aspect, the present invention provides an electronic device including a processor and a memory storing execution instructions. When the processor executes the execution instructions stored in the memory, the processor executes the method described in any one of the first aspect.

[0034] The present invention provides a property service method and apparatus based on artificial intelligence technology. By combining artificial intelligence technology, the consultation information of users is analyzed and classified, and various property services are specifically completed according to different categories, improving the service efficiency and the stability of service quality, realizing automated property services, and reducing the dependence on manpower.

[0035] The further effects of the above non-conventional preferred methods will be described in conjunction with specific embodiments below. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the existing technical solutions, the following will briefly introduce the drawings required for use in the description of the embodiments or the existing technical solutions. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0037] Figure 1 It is a schematic flowchart of a property service method based on artificial intelligence technology provided by an embodiment of the present invention;

[0038] Figure 2 It is a schematic flowchart of another property service method based on artificial intelligence technology provided by an embodiment of the present invention;

[0039] Figure 3 It is a schematic structural diagram of a property service apparatus based on artificial intelligence technology provided by an embodiment of the present invention;

[0040] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0042] At the present stage, the property services in the community are often provided directly by property personnel to the owners, that is, the traditional manual services. The types of property services are diverse, and service personnel often need to perform their respective duties. For example, it can include transactional services (such as paying fees and handling various procedures), functional services (such as construction and maintenance), parking management, and various daily affairs in the community, etc.

[0043] In reality, such a service method mainly relying on manpower may be less efficient, and the service quality is not stable. In addition, the number of service personnel is limited, and it is usually difficult to be proficient in cross-category service content. Therefore, many times, the problems of the owners cannot be solved in the first place.

[0044] For example, when the owner needs to go through certain procedures, but perhaps the relevant staff is not present at that time. And the actual on-duty personnel are mainly responsible for other services (such as exactly being a maintenance worker), and they are not familiar with the services currently required by the owner or are not proficient in the operation. This is very likely to cause the problems of the owner not to be solved. Even in some cases, due to the complexity of property work, for some special services, even professional personnel may not have mastered them proficiently and need to consult relevant materials and systems to be able to explain clearly. These have all led to the situation of low service efficiency and unstable service quality.

[0045] That is to say, in the prior art, there is a lack of a property service method that does not rely on manpower or reduces the reliance on manpower, and it is impossible to achieve automated property services.

[0046] In view of this, the present invention provides a property service method based on artificial intelligence technology. See Figure 1 As shown, it is a specific embodiment of the property service method based on artificial intelligence technology provided by the present invention. In this embodiment, the method includes:

[0047] Step 101: Receive consultation information, use a pre-established language model to determine the service category corresponding to the consultation information, and determine the keyword information in the consultation information.

[0048] In this embodiment, artificial intelligence technology will be utilized, or in other words, property services will be provided based on an artificial intelligence model. The artificial intelligence model may include a language model and a service model, and the service model further includes at least one business sub-model. Each business sub-model is specifically responsible for a corresponding type of business. The consultation information refers to the information input by the property owner into the artificial intelligence model. The consultation information represents a specific business requirement.

[0049] Essentially, the consultation information can be a piece of text. For example, "How much is the property fee this year?" or "Please repair the lighting in the corridor of Unit 3" and so on. This text can be directly input into the model, and the model can analyze the specific requirements of the property owner and further complete the relevant work.

[0050] Specifically, the text should first be input into the language model, which can analyze the text and identify the semantics therein. Before that, data training can be carried out based on the historical property consultation data to establish the language model. Generally, in the property service scenario, the language interaction content is relatively fixed, so targeted training using the historical property consultation can meet the scenario requirements, and it is not necessary to rely on large language models such as ChatGPT and DeepSeek. In this embodiment, the specific data training process is not limited, and any solution that can achieve a similar effect can be combined into the overall technical solution of this embodiment.

[0051] The language model first analyzes the consultation information to obtain the service category corresponding to the consultation information and determine the keyword information in the consultation information. Specifically, semantic analysis can be performed on the consultation information to determine the service requests included in the consultation information; the service category can be determined according to the service requests; and the keyword information can be determined in the service requests.

[0052] In this embodiment, the service categories include transaction services, functional services, and query services. Transaction services generally refer to clerical service contents, which can include various payments, handling of various procedures, signing of contracts, and so on. Functional services generally refer to service items that require on-site operations, such as equipment maintenance, cleaning, garden maintenance, various construction projects, and so on. Query services generally refer to consultations on various matters, that is, mainly answering the questions of property owners and sending various notices to property owners.

[0053] By analyzing the consultation information, the language model can discover the service requests of the property owner, and then classify them to confirm which specific service category they belong to. For example, the above "How much is the property fee this year?" can belong to the query service (it can be considered an inquiry and only the amount needs to be answered), or it can belong to the transaction service (because it means that the user may have a potential desire to pay the fee as soon as possible). And "Please repair the lighting in the corridor of Unit 3" obviously belongs to the functional service.

[0054] The language model can also extract keyword information from the service requests. The keyword information includes keyword fields and key data. Keyword fields generally can represent more specific service items. For example, in "How much is the property fee this year?", the keyword field can be "property fee". In "Please repair the lighting in the corridor of Unit 3", the keyword fields can be "repair" and "lighting". Key data represents some specific parameters to further determine the specific location, specific situation, etc. of the project. For example, in "Please repair the lighting in the corridor of Unit 3", only determining the keyword fields still cannot complete this service because it is still unknown which lighting to "repair", so it is necessary to further confirm the key data "Unit 3" (of course, generally in the system, the lighting in Unit 3 will have a digital code representing its identity, and no further examples will be given here).

[0055] Step 102: According to the service category, call the corresponding business sub-model from the pre-established service model.

[0056] As known above, the artificial intelligence model involved in this embodiment includes a service model, and the service model includes at least one business sub-model. Each business sub-model is specifically responsible for a corresponding type of business. When the business category includes transactional services, functional services, and query services, the business sub-models correspondingly include transaction sub-models, functional sub-models, and query sub-models. Each sub-model specifically processes a type of related business. That is to say, if the business category is transactional services, the transaction sub-model is called. Similarly, for functional services, the functional sub-model is called, and for query services, the query sub-model is called.

[0057] The service model, or each business sub-model, may be pre-established. Specifically, data training can be performed based on historical data of specific categories of services to establish the business sub-model. That is to say, use the historical data of transactional services to train the transaction sub-model, use the historical data of functional services to train the functional sub-model, and use the historical data of query services to train the query sub-model. In this embodiment, the specific data training process is not limited, and any solution that can achieve similar effects can be combined in the overall technical solution of this embodiment.

[0058] After completing the training of the business sub-models, integrate the business sub-models together, that is, establish the service model.

[0059] Step 103: Use the business sub-model to analyze the keyword information to determine the corresponding service process.

[0060] Using a language model, a specific category of business sub-model can be selected to obtain keyword information and input it into the business sub-model. The business sub-model can further analyze the above keywords to determine a targeted service process. Specifically, the business sub-model can use the keyword fields to determine a service template. Using the service template and based on the key data, a service process can be determined.

[0061] Still taking the above example of "Please repair the lighting in the corridor of Unit 3" as an example, the specific business sub-model is a functional sub-model. The keyword fields can be "repair" and "lighting". The key data can be "Unit 3". In this case, a service template dedicated to "repairing lamps" can be determined, and then the key data, that is, "Unit 3", can be filled into the template to obtain the service process for repairing the lighting in Unit 3. In addition, the model can also select the specific model of the lamp in the service process, select specific maintenance personnel according to the shift schedule, determine the maintenance time, determine the tools and consumables required for maintenance, and even determine the route of the personnel to formulate a specific work arrangement. This organically combines specific work items with the overall work plan of the personnel, fully improving work efficiency.

[0062] It should also be noted that for different business categories, the corresponding service processes will also be different. In this embodiment, there are two specific situations:

[0063] When the service category is a transactional service or a functional service, the determination of the service process includes: determining a to-be-executed plan, and the to-be-executed plan includes execution time information, execution location information, execution personnel information, execution tool information, and / or execution program information.

[0064] For transactional services or functional services, there are usually specific matters that need to be specifically operated by staff to be implemented. For example, in transactional services, generally, staff need to perform some paperwork (such as collecting money, issuing receipts, signing and stamping, etc.). In functional services, workers need to complete specific work such as maintenance, installation, and construction on-site. Therefore, for the above two service categories, specific execution plans need to be given to clarify execution time information, execution location information, execution personnel information, execution tool information, and / or execution program information. This makes it fully executable.

[0065] When the service category is a query service, the determination of the service process includes: determining feedback information.

[0066] The characteristics of query services are different. For this type of service, usually, the owner raises a question and needs an answer. Therefore, in this case, generally, no actual operation needs to be carried out, and only feedback information needs to be provided.

[0067] Of course, in some other cases, the service categories can be converted or run in parallel. For example, in some cases, multiple categories of services may be required simultaneously to fully meet the needs of the property owner. This type of situation will be described in detail in the subsequent embodiments.

[0068] Step 104: Execute the service process.

[0069] After determining the service process, just execute it according to this, and the service required by the property owner is completed. If the service process is a specific implementation plan, it should be completed according to the plan. If the service process is feedback information, then send this information to the property owner, which is considered completed.

[0070] As can be seen from the above technical solutions, the beneficial effects of this embodiment are as follows: By combining artificial intelligence technology, the consultation information of users is analyzed and classified, and various property services are completed specifically according to different categories, improving the service efficiency and the stability of service quality, realizing automated property services, and reducing the dependence on human resources.

[0071] Figure 1 The shown is only the basic embodiment of the method of the present invention. Based on this, with certain optimizations and expansions, other preferred embodiments of the method can also be obtained.

[0072] As Figure 2 shown, it is another specific embodiment of the property service method based on artificial intelligence technology of the present invention. In this embodiment, a specific property service scenario will be used as an example for illustration. This scenario is the installation application for a charging pile for new energy vehicles. Currently, many new energy vehicle users can install private charging piles in their private parking spaces. However, the installation procedure of the charging pile is relatively cumbersome, and in some cases, the property management, power company, and construction party need to intervene, involving procedures and contracts of multiple parties; after all procedures are completed, it also involves specific construction. That is to say, it is necessary to involve the above-mentioned transactional services or functional services simultaneously. In the existing mode, the property owner needs to complete each item in sequence. On the one hand, it is difficult to sort out the correct operation sequence, and on the other hand, it is necessary to connect with each party by oneself, spending a lot of time. In this embodiment, artificial intelligence technology can be used to assist the property owner in clarifying the program steps and help the property owner automatically complete various operations during this period.

[0073] In this embodiment, the method includes the following steps:

[0074] Step 201: Receive consultation information, perform semantic analysis on the consultation information, and determine the service demands included in the consultation information.

[0075] Step 202: Determine the service category according to the service demands; according to the service category, call the corresponding business sub-model from the pre-established service model.

[0076] Step 203: Determine the keyword information in the service request; the keyword information includes keyword fields and key data.

[0077] Step 204: Use the business sub-model, use the keyword fields to determine the service template; use the service template and determine the service process according to the key data.

[0078] Step 205: Execute the service process.

[0079] In this embodiment, the consulting information is the application of the property owner for installing a charging pile. The above services often involve two categories, namely transactional services or functional services. And usually, transactional services come first and functional services come later. That is to say, generally, relevant procedures need to be completed and contracts need to be signed in transactional services before entering functional services.

[0080] At this time, the service template can be retrieved through transactional services first, and the property owner can be further prompted to provide relevant materials. For example, real estate certificate, parking space property right certificate / parking space lease agreement, car purchase contract, driving license, etc. The above information can all be regarded as keyword information. Thus, it can be confirmed that the property owner meets the conditions for applying to install a charging pile, and the procedures and contract signing can be automatically completed according to the keyword fields and key data therein. In addition, relevant parties (such as power companies or construction parties) can also be connected to the system to directly participate in the review, certification, and contract signing.

[0081] After that, the business can enter the stage of functional services. At this time, the service template in functional services can be further retrieved to determine the specific installation procedure, installation date, and installation location. Then, the construction party can provide an installation plan. After all the above are approved, more specific installation work can be carried out. In the construction and installation stage, generally, the power company needs to enter the site first to install a special meter for new energy vehicle charging for the property owner. Then, the construction party of the charging pile needs to enter the site to complete further work such as line deployment and charging pile construction and installation. Thus, the entire process of charging pile installation is completed.

[0082] With the service model in this embodiment, on the one hand, it can gradually prompt the property owner about the matters to be handled, guide them to provide materials, and enable them to easily sort out the specific handling process. On the other hand, it can automatically complete transactional service procedures such as applications, approvals, and signings, and can also complete functional service procedures such as installation appointments. This makes the handling process as automated and simplified as possible. This also reflects that the method in the present invention can handle relatively complex property services and can achieve collaborative services among multiple service categories.

[0083] Such as Figure 3As shown, it is a specific embodiment of a property service device based on artificial intelligence technology according to the present invention. The device in this embodiment, that is, the physical device for executing Figures 1 - 2 the method described above. Its technical solution is essentially the same as that of the above embodiment, and the corresponding descriptions in the above embodiment also apply to this embodiment. The device described in this embodiment includes:

[0084] A semantic analysis module 301, configured to receive consultation information, determine the service category corresponding to the consultation information by using a pre-established language model, and determine the keyword information in the consultation information.

[0085] A service classification module 302, configured to call a corresponding business sub-model from a pre-established service model according to the service category.

[0086] A process determination module 303, configured to analyze the keyword information by using the business sub-model to determine the corresponding service process.

[0087] A service execution module 304, configured to execute the service process.

[0088] In this embodiment, property services will be provided by using artificial intelligence technology, or in other words, based on an artificial intelligence model. The artificial intelligence model may include a language model and a service model, and the service model further includes at least one business sub-model. Each business sub-model is specifically responsible for a corresponding type of business. The consultation information refers to the information input by the owner to the artificial intelligence model. The consultation information represents a certain specific business requirement.

[0089] The language model first parses the consultation information to obtain the service category corresponding to the consultation information, and determines the keyword information in the consultation information. Specifically, the consultation information can be semantically analyzed to determine the service demands included in the consultation information; the service category is determined according to the service demands; the keyword information is determined in the service demands;

[0090] In this embodiment, the service categories include transaction services, functional services, and query services. Transaction services generally refer to clerical service contents, which may include various payments, handling of various procedures, signing of contracts, etc. Functional services generally refer to service items that require on-site operations, such as equipment maintenance, cleaning, garden maintenance, various construction projects, etc. Query services generally refer to consultations on various matters, that is, mainly answering the questions of the owner and sending various notices to the owner.

[0091] The language model can also extract keyword information from the service demands. The keyword information includes keyword fields and key data.

[0092] Each business sub-model is specifically responsible for a corresponding type of business. When the business categories include transaction services, functional services, and query services, the business sub-models correspondingly include transaction sub-models, functional sub-models, and query sub-models. Each sub-model specifically processes a related type of business. That is to say, if the business category is transaction services, the transaction sub-model is called. Similarly, for functional services, the functional sub-model is called, and for query services, the query sub-model is called.

[0093] The service model, or each business sub-model, may be established in advance. Specifically, data training can be performed based on service historical data of a specific category to establish the business sub-model. That is to say, the transaction sub-model is trained using the historical data of transaction services, the functional sub-model is trained using the historical data of functional services, and the query sub-model is trained using the historical data of query services. In this embodiment, the specific data training process is not limited, and any solution that can achieve a similar effect can be incorporated into the overall technical solution of this embodiment.

[0094] After completing the training of the business sub-models, the business sub-models are integrated together, that is, the service model is established.

[0095] A language model can be used to select a business sub-model of a specific category, obtain keyword information and input it into the business sub-model. The business sub-model can further analyze the above keywords to determine a targeted service process. Specifically, the business sub-model can use the keyword fields to determine a service template. Using the service template and based on the key data, a service process is determined.

[0096] After determining the service process, just execute it according to this, and the service required by the owner is completed. If the service process is a specific execution plan, it should be executed according to the plan. If the service process is feedback information, then send this information to the owner, and it is considered completed.

[0097] In addition, on the basis of the Figure 3 shown embodiment, preferably, it further includes:

[0098] A language model training module 305, which is used to perform data training based on property consultation historical data to establish the language model.

[0099] A service model training module 306, which is used to perform data training based on service historical data of a specific category to establish the business sub-model; and establish the service model using at least one of the business sub-models.

[0100] The semantic analysis module 301 includes:

[0101] An appeal extraction unit 311, which is used to perform semantic analysis on the consultation information to determine the service appeals included in the consultation information.

[0102] Classification unit 312, configured to determine the service category according to the service request; the service category includes transaction services, function services, and query services.

[0103] Keyword extraction unit 313, configured to determine the keyword information in the service request; the keyword information includes keyword fields and key data.

[0104] The service classification module 302 includes:

[0105] Field processing unit 321, configured to determine a service template by using the keyword fields.

[0106] Process processing unit 322, configured to determine a service process by using the service template and according to the key data.

[0107] The process processing unit 322 includes:

[0108] Execution subunit 3221, configured to determine an execution plan when the service category is a transaction service or a function service; the execution plan includes execution time information, execution location information, execution personnel information, execution tool information, and / or execution program information.

[0109] Feedback subunit 3222, configured to determine feedback information when the service category is a query service.

[0110] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0111] The processor, the network interface, and the memory can be interconnected through an internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 4It is represented only by a bidirectional arrow, but it does not mean that there is only one bus or one type of bus.

[0112] A memory for storing executable instructions. Specifically, the executable instructions are computer programs that can be executed. The memory may include a memory and a non-volatile memory, and provide the executable instructions and data to the processor.

[0113] In a possible implementation, the processor reads the corresponding executable instructions from the non-volatile memory into the memory and then runs them, or can obtain the corresponding executable instructions from other devices to form a property service device based on artificial intelligence technology at the logical level. The processor executes the executable instructions stored in the memory to implement the property service method provided in any embodiment of the present invention through the executed executable instructions.

[0114] The above as in the present invention Figure 3 The method executed by the property service device based on artificial intelligence technology provided in the embodiments shown above can be applied to or implemented by the processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor or by instructions in software form. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0115] The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0116] An embodiment of the present invention also provides a readable medium. The readable storage medium stores execution instructions. When the stored execution instructions are executed by a processor of an electronic device, the electronic device can execute the property service method based on artificial intelligence technology provided in any embodiment of the present invention, and is specifically used to execute as Figure 1 or Figure 2 the method shown.

[0117] The electronic device described in each of the foregoing embodiments may be a computer.

[0118] Those skilled in the art should understand that the embodiments of the present invention may be provided as a method or a computer program product. Therefore, the present invention may be implemented in the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware.

[0119] The embodiments of the present invention are described in a progressive manner. The same or similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts may refer to the partial description of the method embodiments.

[0120] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the said element.

[0121] The above are only the embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various changes and modifications can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A property service method based on artificial intelligence technology, characterized in that: include: Receive consulting information, determine the service category corresponding to the consulting information using a pre-established language model, and determine keyword information in the consulting information; According to the service category, calling the corresponding business sub-model from the pre-established service model; Analyzing the keyword information using the business sub-model to determine a corresponding service process; Execute the service process.

2. The method according to claim 1, characterized in that: Also includes: Data training is performed based on historical property consultation data to establish the language model.

3. The method according to claim 1, characterized in that: Also includes: Performing data training based on service history data of a specific category to establish the business sub-model; The service model is established using at least one of the business sub-models.

4. The method according to any one of claims 1 to 3, characterized in that: The method of using a pre-established language model to determine the service category corresponding to the consulting information and determining the keyword information in the consulting information includes: Performing semantic analysis on the consulting information to determine the service demands included in the consulting information; Determine the service category according to the service demand; the service category includes transaction services, functional services and query services; The keyword information is determined in the service request; the keyword information includes key fields and key data.

5. The method according to claim 4, characterized in that: The business sub-model includes a transaction sub-model, a function sub-model and a query sub-model; the use of the business sub-model to analyze the keyword information to determine the corresponding service process includes: Determine a service template using the key fields; The service process is determined using the service template and according to the key data.

6. The method according to claim 5, characterized in that: When the service category is a transaction service or a functional service, the service determination process includes: Determine the plan to be executed, wherein the plan to be executed includes execution time information, execution location information, execution personnel information, execution tool information and / or execution procedure information.

7. The method according to claim 5, characterized in that: When the service category is a query service, the service determination process includes: Confirm the feedback information.

8. A property service device based on artificial intelligence technology, characterized in that: include: A semantic analysis module, used to receive consulting information, determine the service category corresponding to the consulting information using a pre-established language model, and determine keyword information in the consulting information; A service classification module, used to call a corresponding service sub-model from a pre-established service model according to the service category; A process determination module, used to analyze the keyword information using the business sub-model to determine the corresponding service process; The service execution module is used to execute the service process.

9. A computer-readable storage medium storing a computer program for executing the property service method based on artificial intelligence technology as described in any one of claims 1 to 7.

10. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the property service method based on artificial intelligence technology as described in any one of claims 1-7.

Images