Vehicle end interaction method and device, vehicle, medium and program

Abstract

The invention relates to the technical field of vehicles, in particular to a vehicle end interaction method and device, a vehicle, a medium and a program, and the method comprises the steps: obtaining interaction data of a user; the inquiry intention of the user is determined according to the interaction data, and the inquiry intention comprises battery state inquiry and battery knowledge inquiry; and calling corresponding processing logic according to the inquiry intention to generate an inquiry result and displaying the inquiry result to the user. Therefore, the problem that the user experience feeling is poor due to the fact that the user cannot know the related information of the vehicle battery in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle-side interaction method, device, vehicle, medium and program. Background Art

[0002] Power batteries are an important component of new energy vehicles, so monitoring the battery status and understanding battery knowledge are one of the most concerning pain points for the majority of new energy vehicle owners.

[0003] In related technologies, the battery status of new energy vehicles can only query basic information such as the current remaining power and current driving range, but users cannot directly query battery health and safety risks. A large amount of battery information is still concentrated in the hands of OEMs and battery manufacturers. Manufacturers have a lot of data and research a lot of complex algorithms, but the results are not disclosed to car owners. It is difficult for car owners to obtain battery information for their vehicles. At the same time, users have very little knowledge about batteries and can only temporarily obtain relevant content from other channels when they encounter problems, resulting in a poor user experience. Summary of the invention

[0004] The present application provides a vehicle-side interaction method, device, vehicle, medium and program to solve the problem in the related art that users cannot understand vehicle battery-related information, resulting in a poor user experience.

[0005] The first aspect of the present application provides a vehicle-side interaction method, comprising the following steps: obtaining user interaction data; determining the user's inquiry intention based on the interaction data, wherein the inquiry intention includes battery status query and battery knowledge query; and calling corresponding processing logic based on the inquiry intention to generate an inquiry result and display it to the user.

[0006] Optionally, determining the user's inquiry intention based on the interaction data includes: rewriting the interaction data to generate fine-tuning data; inputting the interaction data and the fine-tuning data into a large language judgment model, and the large language judgment model generates the user's inquiry intention.

[0007] Optionally, the processing process of the large language model: converting the interaction data and the fine-tuning data into a target format; converting the target formatted data into a feature vector; extracting deep features of the feature vector for semantic analysis to generate the user's query intention.

[0008] Optionally, the training method of the large language model includes: obtaining a historical question-and-answer data set related to battery data to generate training samples, wherein the historical question-and-answer data set includes fine-tuning data and guiding data corresponding to the original data; selecting a target layer that needs to be adjusted for the large language model, and inserting a low-rank matrix into the target layer to reset the original weights, and using the training samples and the reset weights to train the target layer to iteratively update the large language model.

[0009] Optionally, calling the corresponding processing logic according to the inquiry intention generates an inquiry result and displays it to the user, including: if the inquiry intention is to query the battery status, calling the corresponding intention data and algorithm in the first preset database according to the inquiry intention, calculating the battery status according to the intention data and algorithm to generate an inquiry result and display it to the user; if the inquiry intention is to query the battery knowledge, querying the second preset data according to the inquiry intention to generate an inquiry result and display it to the user.

[0010] Optionally, querying the second preset data according to the query intention generates a query result and displays it to the user, including: converting the query intention into a feature vector; calculating the similarity between the feature vector and all feature vectors in the database; screening out feature vectors with a similarity higher than a target threshold as candidate results; generating text containing context information by block integration based on the interaction data and the candidate results; inputting the text containing the context information into target data, and the target data outputs the query result.

[0011] The second aspect of the present application provides a vehicle-side interaction device, including an acquisition module for acquiring user interaction data; a determination module for determining the user's inquiry intention based on the interaction data, wherein the inquiry intention includes battery status query and battery knowledge query; and a calling module for calling the corresponding processing logic according to the inquiry intention to generate an inquiry result and display it to the user.

[0012] A third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the vehicle-side interaction method as described in the above embodiment.

[0013] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to perform the vehicle-side interaction method as described in the above embodiment.

[0014] The fifth aspect of the present application provides a computer program product, including a computer program or instructions, characterized in that when the computer program or instructions are executed, the vehicle-side interaction method described in the above embodiment is implemented.

[0015] Therefore, this application has at least the following beneficial effects:

[0016] The embodiment of the present application can determine whether the user's inquiry intention is battery status inquiry or battery knowledge inquiry based on the user's interaction data; and call the corresponding processing logic according to the inquiry intention to generate an inquiry result and display it to the user, thereby improving the accuracy of battery status query and knowledge acquisition, simplifying the user's operation process, and improving the overall user experience.

[0017] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0019] Figure 1 A flowchart of a method provided according to an embodiment of the present application;

[0020] Figure 2 The overall flow chart of the vehicle-side battery intelligent agent based on the large language model provided according to the embodiment of the present application;

[0021] Figure 3 A flowchart of a collaborative routing module provided according to an embodiment of the present application;

[0022] Figure 4 A flowchart of a battery status query module provided according to an embodiment of the present application;

[0023] Figure 5 A flowchart of a battery knowledge query module provided according to an embodiment of the present application;

[0024] Figure 6 A schematic diagram of a vehicle-side interaction device provided according to an embodiment of the present application;

[0025] Figure 7 It is a schematic diagram of the structure of a vehicle provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0027] The following describes the vehicle-side interaction method, device, vehicle, storage medium and program of the embodiments of the present application with reference to the accompanying drawings.

[0028] Specifically, Figure 1 A flowchart of a vehicle-side interaction method provided in an embodiment of the present application.

[0029] like Figure 1 As shown, the vehicle-side interaction method includes the following steps:

[0030] In step S101, user interaction data is obtained.

[0031] It is understandable that the embodiments of the present application can obtain the user's interaction data to facilitate the subsequent determination of the user's inquiry intention.

[0032] It should be noted that the interactive data of the present application may include voice data or text data, etc., without specific limitation.

[0033] In step S102, the user's inquiry intention is determined according to the interaction data, wherein the inquiry intention includes battery status inquiry and battery knowledge inquiry.

[0034] It can be understood that the embodiments of the present application can determine the user's inquiry intention based on the interaction data, thereby determining that the user's inquiry intention is a battery status query or a battery knowledge query, so as to provide the user with the corresponding results based on the actual inquiry intention, thereby improving the user experience.

[0035] In an embodiment of the present application, determining the user's inquiry intention based on the interaction data includes: rewriting the interaction data to generate fine-tuning data; inputting the interaction data and the fine-tuning data into a large language judgment model, and the large language judgment model generates the user's inquiry intention.

[0036] It can be understood that the embodiment of the present application significantly improves the system's ability to understand the user's query intent by rewriting the interaction data to generate fine-tuning data, and inputting this data together with the original interaction data into the large language judgment model to generate the user's query intent, which not only improves the accuracy and efficiency of the query, but also enhances the user experience.

[0037] In the embodiment of the present application, the processing process of the large language model is as follows: converting the interaction data and the fine-tuning data into a target format; converting the target formatted data into a feature vector; extracting the deep features of the feature vector for semantic analysis to generate the user's query intention.

[0038] The target format

[0039] It can be understood that the embodiments of the present application improve the system's ability to understand user query intent and improve the accuracy and efficiency of queries by converting interaction data and fine-tuning data into a target format and performing feature vector conversion and deep semantic analysis to generate user query intent.

[0040] In an embodiment of the present application, a training method for a large language model includes: obtaining a historical question-and-answer data set related to battery data to generate training samples, wherein the historical question-and-answer data set includes fine-tuning data and guiding data corresponding to the original data; selecting a target layer that needs to be adjusted for the large language model, inserting a low-rank matrix into the target layer to reset the original weights, and using the training samples and the reset weights to train the target layer to iteratively update the large language model.

[0041] It can be understood that the embodiments of the present application can obtain historical question-and-answer data sets related to battery data to generate training samples, and adopt fine-tuning techniques such as low-rank adaptation, select the target layer that needs to be adjusted for the large language model, insert the low-rank matrix into the target layer to reset the original weights, and iteratively update the large language model using the training samples and the reset weights, which significantly improves the system's ability to understand the user's query intent as well as the accuracy and efficiency of the query, and also enhances the user experience.

[0042] In step S103, the corresponding processing logic is called according to the inquiry intention to generate the inquiry result and display it to the user.

[0043] It can be understood that the embodiment of the present application generates accurate query results and displays them to the user by calling the corresponding processing logic according to the user's query intention, thereby improving the accuracy of battery status query and knowledge acquisition, simplifying the user's operation process, and improving the overall user experience.

[0044] In an embodiment of the present application, the corresponding processing logic is called according to the inquiry intention to generate an inquiry result and display it to the user, including: if the inquiry intention is to query the battery status, the corresponding intention data and algorithm in the first preset database are called according to the inquiry intention, and the battery status is calculated according to the intention data and algorithm to generate an inquiry result and display it to the user; if the inquiry intention is to query the battery knowledge, the second preset data is queried according to the inquiry intention to generate an inquiry result and display it to the user.

[0045] The first preset database and the second preset database may be selected according to actual needs without specific limitation.

[0046] It can be understood that the embodiments of the present application can query the corresponding database according to different inquiry intentions to determine the data in the corresponding processing logic to generate inquiry results and display them to the user, which significantly improves the response accuracy and efficiency of the system.

[0047] In an embodiment of the present application, query results are generated and displayed to users based on query intent and second preset data, including: converting the query intent into a feature vector; calculating the similarity between the feature vector and all feature vectors in a database; screening out feature vectors whose similarity is higher than a target threshold as candidate results; generating text containing context information based on block integration of interaction data and candidate results; inputting the text containing context information into target data, and outputting the query results from the target data.

[0048] Among them, the target threshold can be set according to user needs without specific limitation.

[0049] It can be understood that the embodiments of the present application can convert the user's natural language query into a feature vector and calculate the similarity with the feature vector in a preset database, screen out candidate results with high similarity, and integrate the interaction data and context information to generate the final query result, thereby improving the accuracy of battery status query and knowledge acquisition.

[0050] According to the vehicle-side interaction method proposed in the embodiment of the present application, the user's inquiry intention is determined to be battery status query or battery knowledge query based on the user's interaction data; and the corresponding processing logic is called according to the inquiry intention to generate the inquiry result and display it to the user, which improves the accuracy of battery status query and knowledge acquisition, simplifies the user's operation process, and improves the overall user experience.

[0051] The following will be combined Figure 2-Figure 4 The vehicle-side interaction method of this application is described in detail as follows:

[0052] like Figure 2 As shown, the present application includes a collaborative routing module, a battery status query module and a battery knowledge query module, wherein the user input first enters the collaborative routing module, which determines the user's query intention and then distributes it to the battery status query module or the battery knowledge query module; finally, the battery status query module or the battery knowledge query module makes a corresponding output.

[0053] 1. If Figure 3 As shown, the above-mentioned collaborative routing module is mainly composed of a large language model intention rewriting part and a large language model judgment part.

[0054] (1) First, we need to fine-tune a large oracle model suitable for the intent rewriting task by constructing question-answer pairs of queries and intents to form a fine-tuning dataset.

[0055] (2) Use some fine-tuning techniques such as Lora to fine-tune the large prediction model and build a large language model for the intent rewriting task.

[0056] (3) Based on the user input, the user's query intention is rewritten through the fine-tuned large model, and the user's query purpose is clarified and output.

[0057] (4) Input the user intention just output into the large language judgment model. The model here can use fine-tuning technology, or directly use the prompt method.

[0058] If you use fine-tuning technology, you need to prepare {instruction-output} question-answer pairs, such as {"instruction":"I want to know the current battery consistency","output":"Battery status query"}, {"instruction":"I want to know what battery consistency includes","output":"Battery knowledge query"}, train these question-answer pairs with Lora, and merge them into the original model. If the prompt method is used, add guiding sentences to the prompt words when inputting into the model. This guiding sentence can be an example, or a few shot chain of thought, etc. The model then determines whether the user's inquiry intention is to query the battery status or battery knowledge, outputs the judgment result, and calls the next step method.

[0059] (5) The user’s original query is taken as input and passed to the other two modules.

[0060] 2. If Figure 4 As shown in the figure, the battery status query module is mainly composed of a large language model, an algorithm library, and a database. This module receives the results of the collaborative routing module, and according to the user's original query, the large language model determines which battery algorithm and data to use, and then retrieves the data from tbox and imports it into the database, and selects the corresponding algorithm from the algorithm library. After calculation, the calculation results are output to the user.

[0061] (1) Preset some data and battery algorithm operators in the algorithm library. These operators include but are not limited to data cleaning, data preprocessing, outlier processing, battery fault statistics, current SOH, temperature consistency, voltage consistency, insulation resistance analysis, etc.

[0062] (2) Based on the user's original query, the large language model determines which battery algorithm and data to use. The model here can use fine-tuning technology, or it can directly use the prompt method. If fine-tuning technology is used, it is necessary to prepare {instruction-output} question-answer data, such as {"instruction":"I want to know how the battery capacity has changed in the past 30 days","output":"30-Ah points"}, {"instruction":"I want to know the current battery consistency","output":"1-standard deviation"}, train these question-answer pairs with Lora, and merge them into the original model. If the prompt method is used, when inputting into the model, add a guiding sentence to the prompt word. This guiding sentence can be an example, or a few shot chain of thought, etc. Analyze which time period and type of battery status query the user needs to make and the field name that needs to be used.

[0063] (3) Based on the results of the previous step, retrieve the data that meets the conditions in tbox and import it into the database. Then transfer the data and operators to the algorithm platform.

[0064] (4) After the algorithm platform processes, analyzes and calculates the data, it outputs the calculation results to the user.

[0065] 3. If Figure 5 As shown in the figure, the battery knowledge query module is mainly composed of a large language model and a vector database. After receiving the results of the collaborative routing module, the rag process is directly used according to the user's original query to match the user's question with the content in the knowledge base, select the content with high similarity, and input it into the large language model. The large language model integrates the content and user input and outputs the result to the user.

[0066] (1) First, we need to build a vector database containing battery knowledge.

[0067] The battery knowledge is divided into blocks, and each block is then passed through a text vectorization model to convert the text into a vector of fixed length. Finally, these vectors are stored in a vector database for matching.

[0068] (2) Based on the user’s original query, directly use the rag process. First, use the same text vectorization model as in the previous step to convert the user’s question into a vector of fixed length.

[0069] (3) Calculate the similarity between the vector of the user question and the vector content in the knowledge base. You can use cosine similarity or calculate Euclidean distance, and select the blocks with higher similarity in the vector database.

[0070] (4) Integrate the user question and the selected blocks with high similarity to construct a prompt. This prompt needs to include the user question and the selected block results.

[0071] (5) The entire prompt is input into the large language model, which performs semantic understanding and reasoning and outputs the result to the user.

[0072] It should be noted that the methods used in this application to solve technical problems include database query language, PYTHON data processing, analysis and algorithm application.

[0073] The fields that need to be used include VIN code, time, battery cell voltage list, temperature list, etc. Data use requires database support (DBEAVER, SQLSERVER, etc.); data processing analysis and algorithm application require support from PYTHON's pandas, numpy, sklearn, langchain, llamaindex, etc. Large language models used include llama model, ChatGPT, chatglm, QWEN, kimi, etc. Text vectorization models used include M3E-base, etc. Vector databases used include faiss, Elasticsearch, Milvus, etc.

[0074] In summary, this application can directly query the battery information on the vehicle computer, so that the car owner can query the current status of the vehicle's power battery on the vehicle computer, or learn about the battery-related knowledge, so that the car owner can have a deeper understanding of the vehicle's power battery.

[0075] Next, the vehicle-side interaction device proposed according to the embodiment of the present application is described with reference to the accompanying drawings.

[0076] Figure 6 It is a block diagram of the vehicle-side interaction device of an embodiment of the present application.

[0077] like Figure 6 As shown, the vehicle-side interaction device 10 includes: an acquisition module 100, a determination module 200 and a calling module 300.

[0078] Among them, the acquisition module 100 is used to obtain the user's interaction data; the determination module 200 is used to determine the user's inquiry intention based on the interaction data, wherein the inquiry intention includes battery status query and battery knowledge query; the calling module 300 is used to call the corresponding processing logic according to the inquiry intention to generate the inquiry result and display it to the user.

[0079] It should be noted that the aforementioned explanation of the vehicle-side interaction method embodiment is also applicable to the vehicle-side interaction device of this embodiment and will not be repeated here.

[0080] According to the vehicle-side interaction device proposed in the embodiment of the present application, the user's inquiry intention is determined to be battery status inquiry or battery knowledge inquiry based on the user's interaction data obtained; and the corresponding processing logic is called according to the inquiry intention to generate an inquiry result and display it to the user, thereby improving the accuracy of battery status query and knowledge acquisition, simplifying the user's operation process, and improving the overall user experience.

[0081] Figure 7 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0082] A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

[0083] When the processor 702 executes the program, the vehicle-side interaction method provided in the above embodiment is implemented.

[0084] Furthermore, the vehicle also includes:

[0085] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0086] The memory 701 is used to store computer programs that can be executed on the processor 702 .

[0087] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0088] If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0089] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0090] The processor 702 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0091] An embodiment of the present application also provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the vehicle-side interaction method as described above is implemented.

[0092] An embodiment of the present application also provides a computer program product, including a computer program or instructions, characterized in that when the computer program or instructions are executed, the above-mentioned vehicle-side interaction method is implemented.

[0093] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0094] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0095] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0096] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0097] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

Claims

1. A vehicle-side interaction method, characterized in that: The following steps are involved: Get user interaction data; Determining the user's inquiry intention according to the interaction data, wherein the inquiry intention includes battery status inquiry and battery knowledge inquiry; According to the query intention, the corresponding processing logic is called to generate the query result and display it to the user.

2. The vehicle-side interaction method according to claim 1, characterized in that: Determining the user's inquiry intention according to the interaction data includes: Rewrite the interaction data to generate fine-tuning data; The interaction data and the fine-tuning data are input into a large language judgment model, and the large language judgment model generates a user's query intention.

3. The vehicle-side interaction method according to claim 2, characterized in that: The processing process of the large language model: converting the interaction data and the fine-tuning data into a target format; Convert the target formatted data into a feature vector; The deep features of the feature vector are extracted to perform semantic analysis to generate the user's query intention.

4. The vehicle-side interaction method according to claim 2, characterized in that: The training method of the large language model: Obtain a historical question-answer pair dataset related to battery data to generate training samples, wherein the historical question-answer dataset includes fine-tuning data and guiding data corresponding to the original data; Select a target layer that needs to be adjusted in the large language model, insert a low-rank matrix into the target layer to reset the original weights, and use the training samples and the reset weights to train the target layer to iteratively update the large language model.

5. The vehicle-side interaction method according to claim 1, characterized in that: The calling of corresponding processing logic according to the inquiry intention to generate an inquiry result and display it to the user includes: If the inquiry intention is to inquire about the battery status, then the corresponding intention data and algorithm in the first preset database are called according to the inquiry intention, and the battery status is calculated according to the intention data and algorithm to generate an inquiry result and display it to the user; If the inquiry intention is a battery knowledge inquiry, the second preset data is queried according to the inquiry intention to generate an inquiry result and display it to the user.

6. The vehicle-side interaction method according to claim 5, characterized in that: The second preset data is queried according to the inquiry intention to generate an inquiry result and display it to the user, including: Convert the inquiry intention into a feature vector; Calculate similarity between the feature vector and all feature vectors in a database; Filter out feature vectors whose similarity is higher than the target threshold as candidate results; Generate text containing context information by integrating the interaction data and the candidate results in blocks; The text containing the context information is input into target data, and the target data outputs a query result.

7. A vehicle-side interaction device, characterized in that: include: An acquisition module is used to acquire user interaction data; A determination module, used to determine the user's inquiry intention according to the interaction data, wherein the inquiry intention includes battery status inquiry and battery knowledge inquiry; The calling module is used to call the corresponding processing logic according to the inquiry intention to generate the inquiry result and display it to the user.

8. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle-side interaction method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by the processor, it is used to implement the vehicle-side interaction method as described in any one of claims 1-6.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed, the vehicle-side interaction method as described in any one of claims 1-6 is implemented.

Images