Task processing method and system based on multiple expert layers, terminal and medium

Abstract

The invention belongs to the field of natural language processing, and particularly discloses a task processing method and system based on multiple expert layers, a terminal and a medium, a multi-layer expert network is constructed, and the multi-layer expert network comprises a basic expert layer used for processing general field tasks, a field expert layer used for processing a plurality of specific field tasks and a task expert layer used for processing a plurality of task types; receiving an input task, and analyzing the input task to obtain task characteristics of the input task, including a task field, a task type and task complexity; formulating an expert selection strategy according to the task characteristics; and according to the expert selection strategy, inputting the input task into the target expert layer for processing to obtain a processing result. According to the method, the multi-layer expert network is constructed, the corresponding expert layer is selected according to the task characteristics, adaptation to multiple fields and multiple tasks is achieved, the flexibility and pertinence of the model are improved, and the task processing efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the field of natural language processing, and in particular relates to a task processing method, system, terminal and medium based on multiple expert layers. Background Art

[0002] At present, natural language processing (NLP) technology has been widely used in many fields. Among them, pre-trained language models based on the Transformer architecture have become a hot topic of research due to their excellent performance. These models can learn rich language representations by pre-training on large-scale text data. When facing specific fields or tasks, these models require a large amount of fine-tuning data and computing resources to achieve ideal results.

[0003] Current large model systems can often only handle a single type of task in a single field, and are unable to effectively and dynamically adjust the model structure based on task characteristics or field requirements, resulting in the model's lack of flexibility and specificity when dealing with different tasks. Summary of the invention

[0004] To solve the above problems, the present invention provides a task processing method, system, terminal and medium based on multiple expert layers. By constructing a multi-layer expert network and selecting the corresponding expert layer according to the task characteristics, it can achieve adaptation to multiple fields and multiple tasks, improve the flexibility and pertinence of the model, and improve the task processing efficiency.

[0005] In a first aspect, the technical solution of the present invention provides a task processing method based on multiple expert layers, comprising the following steps: Construct a multi-layer expert network, including a basic expert layer for processing general domain tasks, a domain expert layer for processing several specific domain tasks, and a task expert layer for processing several types of tasks; Receive input tasks, analyze the input tasks to obtain task characteristics of the input tasks, including task domain, task type and task complexity; Formulate expert selection strategies based on task characteristics; According to the expert selection strategy, the input task is input into the target expert layer for processing to obtain the processing result.

[0006] In an optional implementation, analyzing the input task to obtain the task characteristics of the input task specifically includes: Extract keywords from the input task and obtain the task domain through keyword matching algorithm; Process the input task based on the pre-trained classification model to obtain the task type; The input task is processed based on the pre-trained language model to obtain the task complexity.

[0007] In an optional implementation, an expert selection strategy is formulated according to task characteristics, specifically including: Pre-configure expert selection strategy configuration rules; Based on the expert selection strategy configuration rules, an expert selection strategy is formulated according to the task characteristics.

[0008] In an optional implementation, based on the expert selection strategy configuration rule, an expert selection strategy is formulated according to task characteristics, specifically including: Detection task area; If the task domain is a general domain, the task complexity is detected, and the basic expert layer is selected as the target expert layer according to the task complexity, or the basic expert layer and the task expert layer are selected as the target expert layer, wherein the task expert layer is a task expert layer adapted to the task type; including if the task complexity is low complexity, only the basic expert layer is selected as the target expert layer to process the input task, and if the task complexity is medium or high complexity, a combination of the basic expert layer and the task expert layer is selected to process the input task; If the task domain is a specific domain, the task complexity is detected, and the domain expert layer is selected as the target expert layer according to the task complexity, or at least one of the basic expert layer, the task expert layer and the domain expert layer are selected as the target expert layer, wherein the domain expert layer is a domain expert layer adapted to the task domain, and the task expert layer is a task expert layer adapted to the task type; including if the task complexity is low complexity, only the domain expert layer is selected, if the task complexity is medium complexity, the basic expert layer and the domain expert layer are selected, and if the task complexity is high complexity, the basic expert layer, the domain expert layer and the task expert layer are selected.

[0009] In an optional implementation, before inputting the input task into the target expert layer for processing to obtain the processing result according to the expert selection strategy, the following steps are also included: The number of detection target expert layers; If the number of target expert layers is greater than 1, the pre-trained gating network is used to configure weights for each target expert layer based on task complexity and task domain; Among them, for the i-th expert layer, the weight of the gating network output is Calculated by the following formula,

[0010] In the formula, is a learned parameter that represents the influence of complexity, domain characteristics, and constants. is an activation function, is the task complexity, For domain characteristics.

[0011] In an optional implementation, the input task is input into the target expert layer for processing to obtain a processing result according to the expert selection strategy, specifically including: If there is one target expert layer, the input task is input into the target expert layer for processing, and the output of the target expert layer is the processing result; If the number of target expert layers is greater than one, the input task is input into each target expert layer to obtain the processing result according to the level and weight of the target expert layer.

[0012] In an optional implementation, according to the level and weight of the target expert layer, inputting the input task into each target expert layer to obtain the processing result specifically includes: The levels of basic experts, domain experts, and task experts increase in sequence; Input the task to the target expert layer at the lowest level to obtain the current output, multiply the current output by the weight of the target expert layer at the lowest level and input it as input data to the target expert layer at the next level, and so on, until the target expert layer at the highest level completes processing and obtains the output, and multiply the output of the target expert layer at the highest level by the weight of the target expert layer at the highest level as the processing result.

[0013] In a second aspect, the technical solution of the present invention provides a task processing system based on multiple expert layers, comprising: A multi-layer expert network building module is used to build a multi-layer expert network, including a basic expert layer for processing general domain tasks, a domain expert layer for processing several specific domain tasks, and a task expert layer for processing several task types; An input task characteristic analysis module is used to receive an input task and analyze the input task to obtain the task characteristics of the input task, including task domain, task type and task complexity; Expert selection strategy formulation module, used to formulate expert selection strategy according to task characteristics; The input task processing module is used to input the input task into the target expert layer for processing to obtain the processing result according to the expert selection strategy.

[0014] In a third aspect, the technical solution of the present invention provides a terminal, including: A memory, used for storing a task processing program based on multiple expert layers; A processor is used to implement the steps of any one of the above-mentioned task processing methods based on multiple expert layers when executing the task processing program based on multiple expert layers.

[0015] In a fourth aspect, the technical solution of the present invention provides a computer-readable storage medium, on which is stored a task processing program based on multiple expert layers. When the task processing program based on multiple expert layers is executed by a processor, the steps of the task processing method based on multiple expert layers as described in any one of the above items are implemented.

[0016] The present invention provides a task processing method, system, terminal and medium based on multiple expert layers, which have the following beneficial effects compared with the prior art: first, a multi-layer expert network including a basic expert layer, a domain expert layer and a task expert layer is constructed, and task characteristics of an input task are obtained by any analysis, and a combination of different expert layers is selected from each expert layer as an expert selection strategy according to the task characteristics, and finally, the input task is processed using a target expert layer based on the expert selection strategy. The present invention realizes flexible adjustment of the expert layer combination according to the task characteristics (task domain, task type and task complexity) of different input tasks, thereby realizing task processing of different task types in different domains, improving the adaptability of the model in processing diversified tasks, and by selecting the most appropriate expert layer for processing, improving the accuracy and reliability of the output results, and improving the task processing efficiency and performance. BRIEF DESCRIPTION OF THE DRAWINGS In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 A flowchart of a task processing method based on multiple expert layers is provided in an embodiment of the present invention.

[0018] Figure 2 A schematic block diagram of the structure of a multi-expert-layer task processing system provided by an embodiment of the present invention.

[0019] Figure 3 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in this specific embodiment. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of them. Based on the embodiments in this patent, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this patent.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0022] Figure 1 A flowchart of a task processing method based on multiple expert layers is provided in an embodiment of the present invention. Figure 1 The execution subject may be a task processing system based on multiple expert layers. According to different requirements, the order of the steps in the flowchart may be changed, and some may be omitted. The task processing method based on multiple expert layers provided in the embodiment of the present invention is executed by a computer device, and accordingly, the task processing system based on multiple expert layers runs in the computer device.

[0023] like Figure 1 As shown, the method includes the following steps.

[0024] S1, build a multi-layer expert network.

[0025] The expert network of this embodiment includes three layers of experts, namely a basic expert layer, a domain expert layer and a task expert layer.

[0026] The basic expert layer is used to process general domain tasks and can adopt the BERT architecture. It can include multiple BERT architectures, such as BERT1, BERT2, and BERT3. When selecting the basic expert layer, you can select any one of BERT1, BERT2, and BERT3 as needed, for example, you can select it based on the processing effect.

[0027] The domain expert layer is used to handle tasks in certain specific fields, such as medical, legal, and financial fields. It can be fine-tuned based on domain knowledge and can use models with BERT-like structures, such as BERT, Roberta, etc. For example, the domain expert layer includes BERT4 in the medical field, BERT4 in the medical field, BERT5 in the legal field, and BERT6 in the legal field. When selecting the domain expert layer, you can select BERT in the corresponding field based on the task field and complexity.

[0028] The task expert layer is used to process several task types, such as question answering, text classification, machine translation, etc., and can use models with structures such as RNN and LSTM. For example, the task expert layer includes the sequence labeling task lstm+crf and the classification task softmax. When selecting the task expert layer, you can select the corresponding model according to the task type.

[0029] S2, receiving an input task, analyzing the input task to obtain task characteristics of the input task.

[0030] The task characteristics of this embodiment include task domain, task type and task complexity, and task characteristic analysis is achieved through the following steps.

[0031] S2.1, extract keywords from the input task and obtain the task domain through the keyword matching algorithm.

[0032] For example, the domain features of a medical task may be medical terms, case data, etc.; the domain features of a legal task may be legal provisions, judgments, etc. The domain features can be used to determine which domain the task belongs to by keyword matching.

[0033] S2.2, process the input task based on the pre-trained classification model to obtain the task type.

[0034] BERT is a pre-trained language representation model based on the Transformer architecture. An optional implementation uses BERT to fine-tune a text classification model.

[0035] First, collect and annotate the dataset, where each sample contains the input text and the corresponding task type label, and then divide it into training, validation, and test sets. Use the pre-trained BERT model as a basis. Load a library compatible with BERT, such as Hugging Face's Transformers library. Add a classification head (can be a fully connected layer + Softmax) to the output layer of BERT to match the number of task types. Fine-tune the model using the training data.

[0036] S2.3, process the input task based on the pre-trained language model to obtain the task complexity.

[0037] The task complexity is determined by factors such as the semantic complexity of the input data and the length of the text. For example, long texts or texts containing a lot of proper nouns may have higher complexity, while short texts or ordinary conversations may have lower complexity. Complexity analysis generates a task complexity score by analyzing the features of the input data based on a pre-trained language model (such as BERT).

[0038] S3, formulate expert selection strategy based on task characteristics.

[0039] An optional implementation method is to pre-configure expert selection strategy configuration rules, and formulate expert selection strategies based on the expert selection strategy configuration rules and task characteristics. It should be noted that the expert selection strategy is a combination of various expert layers.

[0040] An optional implementation method is to formulate an expert selection strategy based on the expert selection strategy configuration rule according to the task characteristics, which specifically includes the following steps.

[0041] S3.1, detection task area.

[0042] S3.2, if the task domain is a general domain, the task complexity is detected, and the basic expert layer is selected as the target expert layer according to the task complexity, or the basic expert layer and the task expert layer are selected as the target expert layer, where the task expert layer is a task expert layer adapted to the task type.

[0043] S3.3, if the task domain is a specific domain, the task complexity is detected, and the domain expert layer is selected as the target expert layer according to the task complexity, or at least one of the basic expert layer, the task expert layer and the domain expert layer are selected as the target expert layer, where the domain expert layer is a domain expert layer adapted to the task domain, and the task expert layer is a task expert layer adapted to the task type.

[0044] In this optional implementation, first determine whether it is necessary to select a domain expert layer based on the task domain, and then select a combination with other expert layers based on the complexity. Exemplarily, the task domain is a general domain. If the task complexity is low-level complexity, only the basic expert layer is selected as the target expert layer to process the input task. If the task complexity is medium or high complexity, a combination of the basic expert layer and the task expert layer is selected to process the input task. When selecting a task expert layer, a specific model is selected based on the task type of the input task. Exemplarily, the task domain is a specific domain. First, the domain expert layer is selected as the target expert layer, and then other expert layers are selected based on the task complexity. For example, if the task complexity is low-level complexity, only the domain expert layer is selected. If the task complexity is medium complexity, the basic expert layer and the domain expert layer are selected. If the task complexity is high complexity, the basic expert layer, the domain expert layer and the task expert layer are selected.

[0045] For example, an input task is a classification task in the legal field, which has a high complexity. The expert selection strategy formulated is basic layer (BERT1) + domain expert layer (legal field BERT4) + task expert layer (classification task Softmax). The selection of each BERT in the basic layer can be pre-configured with selection priorities in different fields, and each BERT in the domain expert layer can be selected according to the complexity of the task.

[0046] S4, inputting the input task into the target expert layer for processing to obtain the processing result according to the expert selection strategy.

[0047] The expert layers finally selected in this embodiment may include multiple ones. To further improve the accuracy of the processing results, after formulating the expert selection strategy in this embodiment, if there are multiple target expert layers, weights are configured for each target expert layer, and the results are output according to the weights, which specifically includes the following steps.

[0048] S4.1, number of detection target expert layers.

[0049] S4.2, if the number of target expert layers is greater than 1, the pre-trained gating network is used to configure weights for each target expert layer according to task complexity and task domain.

[0050] For the i-th expert layer, the weight of the gating network output Calculated by the following formula,

[0051] In the formula, is a learned parameter that represents the influence of complexity, domain characteristics, and constants. is an activation function, is the complexity of the task. The more complex the task, the greater the weight value may be. is a domain feature, which indicates the need for specialized knowledge in the field to which the task belongs. If the task involves a very specific field (such as law, medicine, etc.), the contribution of domain experts may need to be greater. is a constant term used to adjust the fixed contribution of some basic experts (such as the base layer).

[0052] S4.3, if there is one target expert layer, the input task is input into the one target expert layer for processing, and the output of the one target expert layer is the processing result.

[0053] S4.4, if the number of target expert layers is greater than one, input the input task into each target expert layer according to the level and weight of the target expert layer to obtain the processing result.

[0054] In this embodiment, the levels of the basic expert layer, the domain expert layer, and the task expert layer are increased in sequence, that is, the basic expert layer is the lowest level and the task expert layer is the highest level. The target expert layer with the lowest level of the input task is input to obtain the current output, and the current output is multiplied by the weight of the target expert layer with the lowest level as input data to the target expert layer of the next level, and so on, until the target expert layer with the highest level is processed and the output is obtained, and the output of the target expert layer with the highest level is multiplied by the weight of the target expert layer with the highest level as the processing result.

[0055] For example, the target expert layer includes the basic expert layer, the domain expert layer, and the task expert layer, and the weights of each layer are , , , the output of each layer is as follows.

[0056] Base layer output: .

[0057] Domain expert layer output: .

[0058] Task Expert Layer Output: .

[0059] The final processing result is the output of the task expert layer.

[0060] In an optional implementation, when training a multi-layer expert network, the loss function is designed to be a weighted sum of multiple task losses:

[0061] in, is the task loss, usually the loss of the classification or generation task. is the domain loss, which is used to evaluate the expert layer’s ability to capture domain-specific information. is the expert layer loss, which measures the performance of different expert layers and their contribution to the model.

[0062] An embodiment of a multi-expert-layer task processing method is described in detail above. Based on the multi-expert-layer task processing method described in the above embodiment, an embodiment of the present invention further provides a multi-expert-layer task processing system corresponding to the method.

[0063] Figure 2 A schematic block diagram of the structure of a multi-expert layer task processing system provided in an embodiment of the present invention. In this embodiment, the multi-expert layer task processing system 200 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: a multi-layer expert network construction module 210, an input task characteristic analysis module 220, an expert selection strategy formulation module 230, and an input task processing module 240. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory.

[0064] The multi-layer expert network construction module 210 is used to construct a multi-layer expert network, including a basic expert layer for processing general domain tasks, a domain expert layer for processing several specific domain tasks, and a task expert layer for processing several task types.

[0065] The input task characteristic analysis module 220 is used to receive an input task and analyze the input task to obtain the task characteristics of the input task, including task domain, task type and task complexity.

[0066] The expert selection strategy formulation module 230 is used to formulate an expert selection strategy according to task characteristics.

[0067] The input task processing module 240 is used to input the input task into the target expert layer for processing to obtain a processing result according to the expert selection strategy.

[0068] The task processing system based on multiple expert layers of this embodiment is used to implement the aforementioned task processing method based on multiple expert layers. Therefore, the specific implementation method of this system can be seen in the implementation example part of the task processing method based on multiple expert layers in the previous text. Therefore, its specific implementation method can refer to the description of the corresponding embodiments of each part, which will not be elaborated here.

[0069] In addition, since the task processing system based on multiple expert layers of this embodiment is used to implement the aforementioned task processing method based on multiple expert layers, its function corresponds to that of the aforementioned method and will not be described in detail here.

[0070] Figure 3 A schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention includes: a processor 310, a memory 320 and a communication unit 330. The processor 310 is used to implement the following steps when implementing the task processing program based on multiple expert layers stored in the memory 320: Construct a multi-layer expert network, including a basic expert layer for processing general domain tasks, a domain expert layer for processing several specific domain tasks, and a task expert layer for processing several types of tasks; Receive input tasks, analyze the input tasks to obtain task characteristics of the input tasks, including task domain, task type and task complexity; Formulate expert selection strategies based on task characteristics; According to the expert selection strategy, the input task is input into the target expert layer for processing to obtain the processing result.

[0071] The present invention also provides a computer storage medium, wherein the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0072] The computer storage medium stores a task processing program based on multiple expert layers, and when the task processing program based on multiple expert layers is executed by the processor, the following steps are implemented: Construct a multi-layer expert network, including a basic expert layer for processing general domain tasks, a domain expert layer for processing several specific domain tasks, and a task expert layer for processing several types of tasks; Receive input tasks, analyze the input tasks to obtain task characteristics of the input tasks, including task domain, task type and task complexity; Formulate expert selection strategies based on task characteristics; According to the expert selection strategy, the input task is input into the target expert layer for processing to obtain the processing result.

[0073] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A task processing method based on multiple expert layers, characterized in that: The following steps are involved: Construct a multi-layer expert network, including a basic expert layer for processing general domain tasks, a domain expert layer for processing several specific domain tasks, and a task expert layer for processing several types of tasks; Receive input tasks, analyze the input tasks to obtain task characteristics of the input tasks, including task domain, task type and task complexity; Formulate expert selection strategies based on task characteristics; According to the expert selection strategy, the input task is input into the target expert layer for processing to obtain the processing result.

2. The task processing method based on multiple expert layers according to claim 1 is characterized in that: Analyze the input task to obtain the task characteristics of the input task, including: Extract keywords from the input task and obtain the task domain through keyword matching algorithm; Process the input task based on the pre-trained classification model to obtain the task type; The input task is processed based on the pre-trained language model to obtain the task complexity.

3. The task processing method based on multiple expert layers according to claim 2 is characterized in that: Formulate an expert selection strategy based on the characteristics of the task, including: Pre-configure expert selection strategy configuration rules; Based on the expert selection strategy configuration rules, an expert selection strategy is formulated according to the task characteristics.

4. The task processing method based on multiple expert layers according to claim 3 is characterized in that: Based on the expert selection strategy configuration rules, an expert selection strategy is formulated according to the task characteristics, including: Detection task area; If the task domain is a general domain, the task complexity is detected, and the basic expert layer is selected as the target expert layer according to the task complexity, or the basic expert layer and the task expert layer are selected as the target expert layer, wherein the task expert layer is a task expert layer adapted to the task type; including if the task complexity is low complexity, only the basic expert layer is selected as the target expert layer to process the input task, and if the task complexity is medium or high complexity, a combination of the basic expert layer and the task expert layer is selected to process the input task; If the task domain is a specific domain, the task complexity is detected, and the domain expert layer is selected as the target expert layer according to the task complexity, or at least one of the basic expert layer, the task expert layer and the domain expert layer are selected as the target expert layer, wherein the domain expert layer is a domain expert layer adapted to the task domain, and the task expert layer is a task expert layer adapted to the task type; including if the task complexity is low complexity, only the domain expert layer is selected, if the task complexity is medium complexity, the basic expert layer and the domain expert layer are selected, and if the task complexity is high complexity, the basic expert layer, the domain expert layer and the task expert layer are selected.

5. The task processing method based on multiple expert layers according to claim 4 is characterized in that: Before inputting the input task into the target expert layer for processing and obtaining the processing result according to the expert selection strategy, the following steps are also included: The number of detection target expert layers; If the number of target expert layers is greater than 1, the pre-trained gating network is used to configure weights for each target expert layer based on task complexity and task domain; Among them, for the i-th expert layer, the weight of the gating network output is Calculated by the following formula, In the formula, is a learned parameter that represents the influence of complexity, domain characteristics, and constants. is an activation function, is the task complexity, For domain characteristics.

6. The task processing method based on multiple expert layers according to claim 5 is characterized in that: According to the expert selection strategy, the input task is input into the target expert layer for processing to obtain the processing results, including: If there is one target expert layer, the input task is input into the target expert layer for processing, and the output of the target expert layer is the processing result; If the number of target expert layers is greater than one, the input task is input into each target expert layer to obtain the processing result according to the level and weight of the target expert layer.

7. The task processing method based on multiple expert layers according to claim 6 is characterized in that: According to the level and weight of the target expert layer, the input task is input into each target expert layer to obtain the processing result, including: The levels of basic experts, domain experts, and task experts increase in sequence; Input the task to the target expert layer at the lowest level to obtain the current output, multiply the current output by the weight of the target expert layer at the lowest level and input it as input data to the target expert layer at the next level, and so on, until the target expert layer at the highest level completes processing and obtains the output, and multiply the output of the target expert layer at the highest level by the weight of the target expert layer at the highest level as the processing result.

8. A task processing system based on multiple expert layers, characterized in that: include: A multi-layer expert network building module is used to build a multi-layer expert network, including a basic expert layer for processing general domain tasks, a domain expert layer for processing several specific domain tasks, and a task expert layer for processing several task types; An input task characteristic analysis module is used to receive an input task and analyze the input task to obtain the task characteristics of the input task, including task domain, task type and task complexity; Expert selection strategy formulation module, used to formulate expert selection strategy according to task characteristics; The input task processing module is used to input the input task into the target expert layer for processing to obtain the processing result according to the expert selection strategy.

9. A terminal, characterized in that: include: A memory, used for storing a task processing program based on multiple expert layers; A processor is used to implement the steps of the task processing method based on multiple expert layers as described in any one of claims 1 to 7 when executing the task processing program based on multiple expert layers.

10. A computer-readable storage medium, characterized in that: The readable storage medium stores a task processing program based on multiple expert layers, and when the task processing program based on multiple expert layers is executed by a processor, the steps of the task processing method based on multiple expert layers as claimed in any one of claims 1 to 7 are implemented.

Images