TWM662550U - Application Service System - Google Patents

Abstract

An application service system is used for communicating with a client electronic device. The application service system is used to: receive an input message from the client electronic device and use a natural language processing model to perform semantic analysis on the input message to generate a semantic analysis result corresponding to the input message; select one of the related functional feature data with the highest matching degree with the semantic analysis result from multiple functional feature data, and transmit a function configuration suggestion corresponding to the related functional feature data to the client electronic device; after receiving an approval notification from the client electronic device and corresponding to the function configuration suggestion, add an interface element corresponding to the related functional feature data to a user interface.

Description

Application Service System

The present invention relates to a service system, and in particular to an application service system involving an application.

The current application program interfaces are all presented in fixed templates, and the interfaces present a wide variety of functions, which makes it difficult for customers to find or understand the various functions. In addition, many functions are not needed by customers, but cannot be adjusted due to the standardized operating interface, resulting in a certain degree of inconvenience for customers.

Therefore, how to develop a suitable application programming interface to improve the smoothness of customer use is the subject of this new model.

Therefore, in order to improve the existing technology, the purpose of the present invention is to provide an application service system that can recommend an application program interface suitable for the user through natural language processing technology.

Therefore, the new application service system is suitable for communicating with a client electronic device, which is used to execute a client application to display a user interface included in the client application; the application service system includes a processing unit and a storage unit electrically connected to the processing unit, and the storage unit stores a natural language processing model and multiple functional feature data, wherein the functional feature data respectively correspond to multiple interface elements that can be presented in the user interface. The processing unit is used to: receive an input message from the client electronic device, and use the natural language processing model to perform semantic analysis on the input message to generate a semantic analysis result corresponding to the input message; select one of the related functional feature data that has the highest degree of match with the semantic analysis result from the functional feature data, and transmit a function configuration suggestion corresponding to the related functional feature data to the client electronic device; after receiving an approval notification from the client electronic device corresponding to the function configuration suggestion, add the interface element corresponding to the related functional feature data to the user interface.

In some implementations of the novel application service system, the storage unit further stores an interface configuration data corresponding to the client electronic device, the interface configuration data indicating the interface element(s) that have been configured in the user interface displayed by the client electronic device; wherein the processing unit is further used to: obtain a common configuration data corresponding to the interface configuration data according to the interface element(s) indicated by the interface configuration data, wherein the common configuration data indicates the interface elements among all the interface elements. , related to one or more commonly used interface components of another plurality of client electronic devices; selecting one of the commonly used interface components that is not configured in the user interface displayed by the client electronic device from the commonly used interface components (etc.) as a recommended interface component, and transmitting a component configuration suggestion corresponding to the recommended interface component to the client electronic device; after receiving an acceptance notification from the client electronic device and corresponding to the component configuration suggestion, adding the recommended interface component to the user interface.

In some implementations of the novel application service system, each interface component corresponds to a service item that can be implemented through the client application, and the storage unit also stores a behavior record data corresponding to a client and related to the client electronic device, and a plurality of component function data corresponding to the interface components, the behavior record data indicates the service items that the client has used, and each component function data indicates the service item corresponding to the corresponding interface component; wherein the processing unit is further used to: select one of the first matching component function data that meets a first matching condition data, and transmits a first configuration suggestion corresponding to the first matching component function data to the client electronic device, wherein, for each component function data, the first matching condition includes: the service item indicated by the component function data matches one of the service items indicated by the behavior record data, and the interface component corresponding to the component function data is not configured in the user interface displayed by the client electronic device; after receiving a first adoption notification from the client electronic device and corresponding to the first configuration suggestion, the interface component corresponding to the first matching component function data is added to the user interface.

In some implementations of the novel application service system, each interface component corresponds to a service item that can be realized through the client application, and the storage unit also stores a behavior record data corresponding to a client and related to the client electronic device, and a plurality of component function data corresponding to the interface components, the behavior record data indicates the service items that the client has used, and each component function data indicates the service item corresponding to the corresponding interface component; wherein the processing unit is further used to: select one of the second matching component function data that meets a second matching condition from the component function data, and transmit a second matching component function data using the second matching condition; A second configuration suggestion generated by the natural language processing model and corresponding to the second matching component function data is sent to the client electronic device, wherein, for each component function data, the second matching condition includes: the number of times the service item indicated by the component function data is indicated in the behavior record data is greater than or equal to a predetermined threshold value, and the interface component corresponding to the component function data is not configured in the user interface displayed by the client electronic device; after receiving a second adoption notification from the client electronic device and corresponding to the second configuration suggestion, the interface component corresponding to the second matching component function data is added to the user interface.

In some implementations of the novel application service system, the service item indicated by the second matching component function data is used as a matching service item; when the processing unit receives location data indicating the current location of the client electronic device and determines, based on the location data, that the client electronic device is currently located within a service geographic range corresponding to the matching service item, it uses the natural language processing model to generate a marketing message indicating the matching service item and transmits the marketing message to the client electronic device.

The effect of the present invention is that the application service system can use the natural language processing model to perform semantic analysis on the input message, and accordingly transmit the function configuration suggestion to the client electronic device, so as to add the interface element corresponding to the associated function feature data to the user interface. In this way, the application service system is equivalent to having semantic recognition, and can match the appropriate application function according to the service scenario requirements described by the customer, so that the user can freely configure a dedicated application interface, so that the purpose of the present invention can be achieved.

Before the present invention is described in detail, it should be noted that, unless otherwise specifically defined, the term "electrically connected" in this patent specification is used to describe the "coupled" relationship between computer hardware (e.g., electronic systems, equipment, devices, units, components), and generally refers to "wired electrical connections" achieved by physically connecting multiple computer hardware through conductors/semiconductor materials, and "radio connections" that achieve wireless data transmission using wireless communication technology (e.g., but not limited to wireless networks, Bluetooth, and electromagnetic induction, etc.). On the other hand, unless otherwise specifically defined, the "electrical connection" described in this patent specification also generally refers to a "direct electrical connection" achieved by directly coupling multiple computer hardware to each other, and an "indirect electrical connection" achieved by indirectly coupling multiple computer hardware through other computer hardware.

Before the present invention is described in detail, it should be noted that the "unit" described in this patent specification represents computer hardware rather than software. For example, a "processing unit" is used to represent computer hardware with data processing functions. On the other hand, the "unit" described in this patent specification can refer to a single computer hardware with a specific function, or a group of computer hardware with similar functions. For example, a "processing unit" can refer to a single processor with data processing functions, but it can also refer to a collection of a group of processors.

Referring to FIG. 1 , an embodiment of the novel application service system 100 is managed by a service organization (such as a bank organization) and is adapted to communicate with a client electronic device 200 to implement application services provided by the service organization via the Internet.

In the actual application of this embodiment, the application service system 100 can be used for multiple client electronic devices to be electrically connected via a network. However, for the convenience of description, this embodiment is only illustrated with reference to the client electronic device 200 in FIG. 1 .

The client electronic device 200 may be, for example, a mobile phone, a tablet computer, a laptop computer, or a desktop computer. The client electronic device 200 is installed with a client application program issued by the service institution. By executing the client application program, the client electronic device 200 can display a user interface included in the client application program, and a user can log in to the application service system 100 of this embodiment with a user account under the operation of a user. Specifically, for example, the client application program is a mobile banking application program, and can implement the online banking service provided by the banking institution, but it is not limited to this.

Furthermore, the user interface is a graphical user interface (GUI) that can present one or more of a plurality of interface elements. Each interface element is, for example, an icon or button that can be clicked, and corresponds to a service item that can be implemented through the client application. For example, the service items corresponding to the interface elements include, for example, "balance inquiry", "transfer operation", "foreign currency exchange", "foreign currency fixed deposit", "fund transaction", "gold passbook", etc.

The application service system 100 is, for example, a server or a server set including multiple servers. Furthermore, the application service system 100 includes a processing unit 1 and a storage unit 2 electrically connected to the processing unit 1, wherein the processing unit 1 is adapted to be electrically connected to the client electronic device 200 via a network, thereby communicating with the client electronic device 200.

The processing unit 1 may include (but is not limited to) at least one of a single-core processor, a multi-core processor, a dual-core mobile phone processor, a microprocessor, a microcontroller, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC) and a radio frequency integrated circuit (RFIC).

The storage unit 2 is a data storage device for storing digital data, and can be, for example, a hard disk. However, in other embodiments, the storage unit 2 can also be implemented as a computer-readable recording medium of different types, or a combination of a plurality of computer-readable recording media.

In this embodiment, the storage unit 2 stores a plurality of functional characteristic data D1, an interface configuration data D2 corresponding to the client electronic device 200, a behavior record data D3 corresponding to the user and related to the client electronic device 200, a plurality of component function data D4, and a natural language processing model M1.

The functional feature data D1 respectively correspond to the interface elements that can be presented by the user interface. In the present embodiment, each functional feature data D1 is a vector data, and is used to describe the service item corresponding to the corresponding interface element. In more detail, for each functional feature data D1, the functional feature data D1 is, for example, the result of converting a functional description text into a semantic vector, and the functional description text is a natural language used to describe the relevant service item. For example, if the relevant service item is "foreign currency exchange", the functional description text may be, for example, "foreign currency cash purchase function: customers exchange foreign currency cash, and the currencies include Japanese yen, US dollars, euros, Canadian dollars, RMB, and Hong Kong dollars", but is not limited to this.

The interface configuration data D2 indicates the interface component(s) that have been configured in the user interface displayed by the client electronic device 200. For example, if the user interface displayed by the client electronic device 200 has been configured with three interface components corresponding to the service items such as "foreign currency fixed deposit", "fund transaction" and "gold passbook", the interface configuration data D2 will indicate the three interface components corresponding to the three service items such as "foreign currency fixed deposit", "fund transaction" and "gold passbook".

The behavior record data D3 indicates the service items that the user has used. In the present embodiment, the behavior record data D3, for example, includes one or more transaction records corresponding to the user. Each transaction record corresponds to one of the service items, and may be, for example, generated by the processing unit 1, or generated through input operations by customer service personnel. For example, each transaction record may be, for example, a balance inquiry transaction record corresponding to the service item of "balance inquiry", a transfer transaction record corresponding to the service item of "transfer operation", or a foreign currency exchange transaction record corresponding to the service item of "foreign currency exchange".

The component function data D4 correspond to the interface components respectively. Moreover, each component function data D4 indicates the service item corresponding to the corresponding interface component, and is used for the processing unit 1 to execute a component function program corresponding to the component function data D4 and used to realize the service item. More specifically, when the client electronic device 200 displays the user interface by executing the client application, when one of the interface components presented in the user interface is clicked, the processing unit 1 will execute the component function program corresponding to the component function data D4 according to the component function data D4 corresponding to the one of the interface components, thereby realizing the service item corresponding to the one of the interface components through the client application.

The natural language processing model M1 is a software module with semantic analysis capabilities, and it can be loaded and run by the processing unit 1. More specifically, in this embodiment, the natural language processing model M1 is a large language model (LLM) implemented with neural network-like technology, such as but not limited to a generative pre-trained transformer-based model (GPT), a language model for dialogue applications (LaMDA), or LLaMA (full name Large Language Model Meta AI), but not limited to this. The natural language processing model M1 can convert input information (voice form data or text form data) into corresponding vector form data, and search and extract the reference data most similar to the input text in the vector database through a similarity algorithm, and generate an output text corresponding to the input text in a natural language. It should be noted that the training method of the natural language processing model M1 and the type of actual algorithm used are not the technical focus of this patent specification, so the details are not described in detail here.

The following describes how the application service system 100 executes an application service method. In this embodiment, the application service method includes, for example, a semantic analysis recommendation program, a high-repetitive group recommendation program, a behavior record recommendation program, and a marketing discount recommendation program. It is additionally noted that the order in which the semantic analysis recommendation program, the high-repetitive group recommendation program, the behavior record recommendation program, and the marketing discount recommendation program are executed by the processing unit 1 can be adjusted, and can also be executed by the processing unit 1 at the same time.

Referring to FIG. 1 and FIG. 2 at the same time, the semantic analysis recommendation procedure of the application service method will be described below.

First, as shown in step S11, the processing unit 1 receives an input message from the client electronic device 200, and uses the natural language processing model M1 to perform semantic analysis on the input message to generate a semantic analysis result corresponding to the input message. After the processing unit 1 generates the semantic analysis result, the process proceeds to step S12.

Specifically, when the user wants to edit the interface elements presented by the user interface, the client electronic device 200 can be operated to log in to the application service system 100 with the user account, so that the client electronic device 200 displays the user interface included in the client application. Then, the user can input the input message (for example, "I need to exchange Japanese yen when going abroad") into the user interface of the client application by voice input or typing, so that the processing unit 1 can use the natural language processing model M1 (i.e. load and run the natural language processing model M1) to perform semantic analysis on the input message to generate the semantic analysis result. Among them, the semantic analysis result is the result of the input message being converted into a vector form.

Next, as shown in step S12 , the processing unit 1 selects one piece of related functional feature data that has the highest matching degree with the semantic analysis result from the functional feature data D1 , and transmits an interface configuration suggestion corresponding to the related functional feature data to the client electronic device 200 .

In more detail, the processing unit 1 matches the semantic analysis result with the functional feature data D1, for example, by using cosine similarity to calculate the degree of matching between each functional feature data D1 and the semantic analysis result, and then uses the functional feature data D1 whose degree of matching with the semantic analysis result is greater than or equal to a preset threshold as the associated functional feature data, but is not limited thereto. In other words, in this embodiment, the processing unit 1 uses the functional feature data D1 that is most similar to the semantic analysis result among the functional feature data D1 as the associated functional feature data.

In this embodiment, the interface configuration suggestion may be, for example: "The 'Foreign Currency Cash Structure' function allows you to exchange foreign currency online and then pick it up at a nearby branch. The exchanged currencies include the Japanese yen you need. Do you want to add this function to the custom screen?"

Then, as shown in step S13, after the processing unit 1 transmits the interface configuration suggestion corresponding to the associated functional characteristic data to the client electronic device 200, when the processing unit 1 receives an approval notification from the client electronic device 200 corresponding to the interface configuration suggestion, the processing unit 1 adds the interface element corresponding to the associated functional characteristic data (for example, the interface element corresponding to the service item of "foreign currency exchange") to the user interface, and updates the interface configuration data D2 at the same time, so that the updated interface configuration data D2 indicates the interface element corresponding to the associated functional characteristic data.

Through the semantic analysis recommendation program, the user can describe the functions he needs in a dialogue, and the processing unit 1 recommends and adds the interface components that meet the needs to the user interface, so that the user can freely adjust and configure the user interface.

Referring to Figures 1 and 3, the highly repetitive group recommendation process of the application service method is described below.

As shown in step S21, the processing unit 1 obtains a common configuration data corresponding to the interface configuration data D2 according to the interface component(s) indicated by the interface configuration data D2. The common configuration data indicates one or more common interface components related to another plurality of client electronic devices among all the interface components. After the processing unit 1 obtains the common configuration data, the process proceeds to step S22.

In this embodiment, the processing unit 1 compares the interface configuration data D2 with other multiple interface configuration data, and generates the common configuration data according to the comparison result. The other multiple interface configuration data are used as multiple reference interface configuration data in this embodiment, and the reference interface configuration data correspond to the other multiple client electronic devices. More specifically, the reference interface configuration data indicate the configuration methods of the interface components by other multiple users. Furthermore, the processing unit 1, for example, first selects one or more similar interface configuration data that are similar to the interface configuration data D2 (for example, more than N interface components indicated are the same as the interface configuration data D2) from the reference interface configuration data, and then generates the commonly used configuration data based on the interface components indicated by the (etc.) similar interface configuration data, but is not limited to this.

Next, as shown in step S22, the processing unit 1 selects one of the commonly used interface components that is not configured in the user interface displayed by the client electronic device 200 (i.e., not indicated by the interface configuration data D2) from the commonly used interface components as a recommended interface component, and transmits a component configuration suggestion corresponding to the recommended interface component to the client electronic device 200. In this embodiment, the processing unit 1 selects the interface component that is indicated by the similar interface configuration data the most times and is not indicated by the interface configuration data D2 among the commonly used interface components as the recommended interface component, but the present invention is not limited thereto.

In this embodiment, the service item of the recommendation interface component is, for example, "Mobile Transfer", and the component configuration suggestion may be, for example: "Other users have configured the 'Mobile Transfer' function. As long as you know the recipient's mobile phone, you can transfer money. It is fast and convenient! Is it necessary to add the 'Mobile Transfer' function to the custom screen?"

Then, as shown in step S23, after the processing unit 1 transmits the component configuration suggestion corresponding to the recommended interface element to the client electronic device 200, when the processing unit 1 receives an acceptance notification corresponding to the component configuration suggestion from the client electronic device 200, the processing unit 1 adds the recommended interface element to the user interface and updates the interface configuration data D2 at the same time, so that the updated interface configuration data D2 indicates the recommended interface element.

Through the highly repeatable group recommendation procedure, the processing unit 1 can find a group with similar interface configuration as the user based on the user's interface configuration data D2 on the client electronic device 200, and recommend to the user interface components that the user is more likely to use but have not yet been configured in the user interface, so that the user can decide whether to pre-add the recommended interface components to the user interface for subsequent use.

Referring to FIG. 1 and FIG. 4 at the same time, the following is an explanation of the behavior record recommendation procedure of the application service method.

As shown in step S31, the processing unit 1 selects one of the first matching component function data that meets a first matching condition from the component function data D4, and transmits a first configuration suggestion corresponding to the first matching component function data to the client electronic device 200. Wherein, for each component function data D4, the first matching condition includes: the service item indicated by the component function data D4 matches one of the service items indicated by the behavior record data D3 (that is, the service item indicated by the component function data D4 is a service item that the user has used), and the interface component corresponding to the component function data D4 is not configured in the user interface displayed by the client electronic device 200 (that is, not indicated by the interface configuration data D2).

For example, if the behavior record data D3 indicates that the user has applied for funds through the counter, telephone or Internet (that is, has used the "fund transaction" service item), but the interface component corresponding to the "fund transaction" service item is not indicated by the interface configuration data D2 (that is, it is not configured in the user interface displayed by the client electronic device 200), in this case, the processing unit 1 will determine that the component function data D4 indicating the "fund transaction" service item meets the first matching condition.

In this embodiment, the first configuration suggestion may be, for example: "If you need to place a fund order, online subscription is more convenient and has reduced fees. You can invest with as little as one hundred dollars! Is it necessary to add the "fund subscription" function to the custom screen?"

Then, as shown in step S32, after the processing unit 1 transmits the first configuration suggestion corresponding to the first matching component function data to the client electronic device 200, when the processing unit 1 receives a first adoption notification from the client electronic device 200 and corresponding to the first configuration suggestion, the processing unit 1 adds the interface element corresponding to the first matching component function data to the user interface.

Through the behavior record recommendation procedure, the processing unit 1 can recommend to the user the interface components that the user is more likely to use but have not yet been configured in the user interface based on the service items that the user has used, so that the user can decide whether to add the recommended interface components to the user interface in advance for subsequent use.

Referring to Figures 1 and 5 at the same time, the following is an explanation of the marketing offer recommendation process of the application service method.

As shown in step S41, the processing unit 1 selects one of the second matching component function data that meets a second matching condition from the component function data D4, and transmits a second configuration suggestion corresponding to the second matching component function data generated by the natural language processing model M1 to the client electronic device 200. Wherein, for each component function data D4, the second matching condition includes: the number of times the service item indicated by the component function data D4 is indicated in the behavior record data D3 (that is, the number of times the service item has been used by the user) is greater than or equal to a predetermined threshold value, and the interface component corresponding to the component function data D4 is not configured in the user interface displayed by the client electronic device 200 (that is, not indicated by the interface configuration data D2).

For example, assume that the service item indicated by one of the component function data D4 is "Taiwan Pay" and the predetermined threshold value is ten. If the behavior record data D3 indicates that the user has used the service item "Taiwan Pay" more than ten times, but the interface configuration data D2 does not indicate the interface component corresponding to "Taiwan Pay", the processing unit 1 will determine that the component function data D4 indicating "Taiwan Pay" meets the second matching condition.

In this embodiment, the second configuration suggestion may be, for example: "You often use Taiwan Pay. From 2024/3/1 to 5/31, you can use the coupon to enjoy up to 50% cash back at major night markets. Is it necessary to add the "Taiwan Pay" function to the custom screen?"

Then, as shown in step S42, after the processing unit 1 transmits the second configuration suggestion generated by the natural language processing model M1 and corresponding to the second matching component function data to the client electronic device 200, when the processing unit 1 receives a second adoption notification from the client electronic device 200 and corresponding to the second configuration suggestion, the processing unit 1 adds the interface element corresponding to the second matching component function data to the user interface and updates the interface configuration data D2 at the same time, so that the updated interface configuration data D2 indicates the interface element corresponding to the second matching component function data.

It is to be supplemented that the processing unit 1 regards the service item indicated by the second matching element function data as a matching service item.

Next, as shown in step S43, the processing unit 1 receives location data indicating the current location of the client electronic device 200, and determines that the client electronic device 200 is currently located in a service geographic range corresponding to the matching service item based on the location data, and generates a marketing message indicating the matching service item using the natural language processing model M1, and transmits the marketing message to the client electronic device 200. The location data is, for example, a real-time positioning result generated and transmitted by the client electronic device 200 using satellite positioning technology (such as GPS). To give another example, in this embodiment, the marketing message may be, for example: "Use Taiwan Pay at xx night market, and you will get 50% rebate for every purchase. You also have exclusive discount coupons to use together, don't forget!"

Through the marketing offer recommendation procedure, the processing unit 1 can recommend to the user interface components that the user is more likely to use but have not yet been configured in the user interface based on the user's actual behavior record of using the service items, and can send marketing messages to the client electronic device 200 in a timely manner based on the current location of the client electronic device 200 to remind the user of currently available offers.

It should be understood that steps S11 to S13, steps S21 to S23, steps S31 to S32, steps S41 to S43 and the flow charts of Figures 2 to 5 of this embodiment are only used to illustrate one possible implementation of the novel application service method. It should be understood that even if the aforementioned steps are merged, split or adjusted in order, if the process after the merger, split or adjustment achieves substantially the same effect in substantially the same way as the embodiment of this patent specification, it still belongs to the implementable aspect of the new application service method. Therefore, steps S11 to S13, steps S21 to S23, steps S31 to S32, steps S41 to S43 of this embodiment and the flowcharts of Figures 2 to 5 are not used to limit the scope of implementation of the new invention.

In summary, by implementing the application service method, the application service system 100 can use the natural language processing model M1 to perform semantic analysis on the input message, and accordingly transmit the function configuration suggestion to the client electronic device 200, so as to add the interface component corresponding to the associated function feature data to the user interface. Furthermore, the application service system 100 can find a group with similar interface configurations to the user based on the user's interface configuration data D2 on the client electronic device 200, and recommend to the user the interface components that the user is more likely to use but have not yet been configured in the user interface, so that the user can decide whether to add the recommended interface components to the user interface in advance for subsequent use. Furthermore, the application service system 100 can recommend to the user the interface components that the user is more likely to use but have not yet been configured in the user interface based on the service items that the user has used before, so that the user can decide whether to add the recommended interface components to the user interface in advance for subsequent use. In addition, the application service system 100 can recommend to the user the interface components that the user is more likely to use but have not yet been configured in the user interface based on the user's actual behavior records of using the service items, and can send marketing messages to the client electronic device 200 in a timely manner based on the current location of the client electronic device 200 to remind the user of currently available discounts. Thereby, the application service system 100 is equivalent to having language recognition, and the user can describe the functions he needs in a dialogue manner, and the application service system 100 recommends and adds the interface components that meet the needs to the user interface, so that the user can freely adjust and configure the user interface, thereby improving the user's stickiness to the client application, so that the purpose of this novel technology can be achieved.

However, the above is only an example of the implementation of the present invention, and it cannot be used to limit the scope of the implementation of the present invention. All simple equivalent changes and modifications made according to the scope of the patent application of the present invention and the content of the patent specification are still within the scope of the present patent.

100: Application service system 1: Processing unit 2: Storage unit 200: Client electronic device D1: Functional feature data D2: Interface configuration data D3: Behavior record data D4: Component function data M1: Natural language processing model S11, S12, S13: Steps S21, S22: Steps S31, S32: Steps S41, S42, S43: Steps

Other features and functions of the present invention will be clearly presented in the implementation method of the reference diagram, in which: Figure 1 is a block diagram, exemplarily representing an implementation of the present application service system; Figure 2 is a flow chart, used to exemplarily illustrate how the implementation of the embodiment implements a semantic analysis recommendation procedure in an application service method; Figure 3 is a flow chart, used to exemplarily illustrate how the implementation of the embodiment implements a high-repetitive group recommendation procedure in an application service method; Figure 4 is a flow chart, used to exemplarily illustrate how the implementation of the embodiment implements a behavior record recommendation procedure in an application service method; and Figure 5 is a flow chart, used to exemplarily illustrate how the implementation of the embodiment implements a marketing offer recommendation procedure in an application service method.

100: Application Service System

1: Processing unit

2: Storage unit

200: Client electronic device

D1: Functional characteristic data

D2: Interface configuration data

D3: Behavioral record data

D4: Component function data

M1: Natural Language Processing Model

Claims (5)

An application service system is suitable for communicating with a client electronic device, the client electronic device is used to execute a client application to display a user interface included in the client application; the application service system includes: a processing unit, suitable for being electrically connected to the client electronic device; and a storage unit, electrically connected to the processing unit, and storing a natural language processing model and a plurality of functional feature data, wherein the functional feature data respectively correspond to a plurality of interface elements that can be presented in the user interface; wherein the processing unit is used to: receive an input message from the client electronic device, and perform semantic analysis on the input message using the natural language processing model to generate a semantic analysis result corresponding to the input message; Selecting one of the related functional feature data with the highest matching degree with the semantic analysis result from the functional feature data, and transmitting a function configuration suggestion corresponding to the related functional feature data to the client electronic device; and After receiving a consent notification corresponding to the function configuration suggestion from the client electronic device, adding the interface element corresponding to the related functional feature data to the user interface. The application service system as described in claim 1, wherein the storage unit further stores an interface configuration data corresponding to the client electronic device, the interface configuration data indicating the interface element(s) that have been configured in the user interface displayed by the client electronic device; the processing unit is further used to: According to the interface element(s) indicated by the interface configuration data, obtain a common configuration data corresponding to the interface configuration data, wherein the common configuration data indicates one or more common interface elements among all the interface elements that are related to another plurality of client electronic devices; Selecting one of the commonly used interface components that is not configured in the user interface displayed by the client electronic device from the commonly used interface components as a recommended interface component, and sending a component configuration suggestion corresponding to the recommended interface component to the client electronic device; and after receiving an acceptance notification corresponding to the component configuration suggestion from the client electronic device, adding the recommended interface component to the user interface. An application service system as described in claim 1, wherein each interface component corresponds to a service item that can be implemented through the client application, the storage unit also stores a behavior record data corresponding to a client and related to the client electronic device, and a plurality of component function data corresponding to the interface components, the behavior record data indicates the service items that the client has used, and each component function data indicates the service item corresponding to the corresponding interface component; the processing unit is also used to: From the component function data, select one of the first matching component function data that meets a first matching condition, and transmit a first configuration suggestion corresponding to the first matching component function data to the client electronic device, wherein, for each component function data, the first matching condition includes: the service item indicated by the component function data matches one of the service items indicated by the behavior record data, and the interface component corresponding to the component function data is not configured in the user interface displayed by the client electronic device; and after receiving a first adoption notification from the client electronic device and corresponding to the first configuration suggestion, add the interface component corresponding to the first matching component function data to the user interface. An application service system as described in claim 1, wherein each interface component corresponds to a service item that can be implemented through the client application, the storage unit also stores a behavior record data corresponding to a client and related to the client electronic device, and a plurality of component function data corresponding to the interface components, the behavior record data indicates the service items that the client has used, and each component function data indicates the service item corresponding to the corresponding interface component; the processing unit is also used to: From the component function data, select one of the second matching component function data that meets a second matching condition, and transmit a second configuration suggestion generated by the natural language processing model and corresponding to the second matching component function data to the client electronic device, wherein, for each component function data, the second matching condition includes: the number of times the service item indicated by the component function data is indicated in the behavior record data is greater than or equal to a predetermined threshold value, and the interface component corresponding to the component function data is not configured in the user interface displayed by the client electronic device; and after receiving a second adoption notification from the client electronic device and corresponding to the second configuration suggestion, add the interface component corresponding to the second matching component function data to the user interface. An application service system as described in claim 4, wherein: the service item indicated by the second matching component function data is used as a matching service item; and the processing unit receives location data indicating the current location of the client electronic device, and when it determines from the location data that the client electronic device is currently located within a service geographic range corresponding to the matching service item, generates a marketing message indicating the matching service item using the natural language processing model, and transmits the marketing message to the client electronic device.

Images