Zero code visualization AI algorithm arrangement method, system and device and medium

Abstract

The invention relates to the technical field of algorithm arrangement, particularly provides a zero-code visualization AI algorithm arrangement method, system and equipment and a medium, and aims to solve the problems that project customization development through AI algorithm arrangement is relatively long in time consumption, has certain operation difficulty and is not visual enough. In order to achieve the purpose, the zero-code visualization AI algorithm arrangement method comprises the steps that a project flow chart created by a user based on a visualization canvas and resource nodes is obtained, and the resource nodes are used for providing data sources, AI algorithm services and logic rules; performing anomaly detection on the project flow chart; and in response to the detection result being normal, converting the project flow chart into a project decision model based on preset execution logic. Through the method, the operation threshold of the user is effectively reduced, and the efficiency of project customization development is improved.

Description

Technical Field

[0001] This application relates to the technical field of algorithm orchestration, and particularly relates to a zero-code visualization AI algorithm orchestration method, system, device, and medium. Background Art

[0002] When using AI (Artificial Intelligence) algorithms to solve practical problems, it is usually necessary to flexibly combine multiple AI algorithms according to the application scenario. For example, select multiple algorithms according to the actual project goals, determine the cooperation methods of multiple algorithms, and build the combination logic of multiple algorithms through programming. However, when using the above methods for customized development of projects, it takes a long time, has a certain degree of operation difficulty, and is not intuitive enough.

[0003] Correspondingly, there is a need in this field for a new zero-code visualization AI algorithm orchestration solution to solve the above problems. Summary of the Invention

[0004] To overcome the above-mentioned defects, this application is proposed to solve or at least partially solve the technical problems that the customized development of projects through AI algorithm orchestration takes a long time, has a certain degree of operation difficulty, and is not intuitive enough.

[0005] In a first aspect, a zero-code visualization AI algorithm orchestration method is provided. The method includes: obtaining a project flow chart created by a user based on a visualization canvas and resource nodes, where the resource nodes are used to provide data sources, AI algorithm services, and logical rules; performing anomaly detection on the project flow chart; and in response to a normal detection result, converting the project flow chart into a project decision model based on a preset execution logic.

[0006] In a technical solution of the above zero-code visualization AI algorithm orchestration method, the project flow chart is obtained by the user dragging multiple resource nodes onto the visualization canvas and creating connection relationships for the multiple resource nodes. The prerequisite for creating connection relationships for the multiple resource nodes is that the modalities of any two resource nodes are aligned.

[0007] In a technical solution of the above zero-code visualization AI algorithm orchestration method, the project flow chart includes at least one input node and at least one output node. The performing anomaly detection on the project flow chart includes: detecting whether there are abnormal situations such as islands, closed loops, no input nodes, or no output nodes in the project flow chart.

[0008] In a technical solution of the above zero-code visualization AI algorithm orchestration method, the method further includes: converting the project flow chart into a first matrix represented by resource nodes and connection relationships between resource nodes for storage.

[0009] In a technical solution of the above zero-code visualization AI algorithm orchestration method, the method further includes: in response to a user querying the project flow chart, echoing the project flow chart on the visualization canvas based on the first matrix.

[0010] In a technical solution of the above zero-code visualization AI algorithm orchestration method, the method further includes: converting the project decision model into a second matrix represented by resource nodes and the execution order between the resource nodes for storage, where the execution order between the resource nodes is determined by the preset execution logic.

[0011] In a technical solution of the above zero-code visualization AI algorithm orchestration method, the method further includes: in response to a user invoking the intelligent decision model, calculating each resource node according to the execution order based on the second matrix.

[0012] In a second aspect, a zero-code visualization AI algorithm orchestration system is provided. The system includes: an acquisition module, configured to acquire a project flow chart created by a user based on a visualization canvas and resource nodes, where the resource nodes are used to provide data sources, AI algorithm services, and logic rules; a detection module, configured to perform anomaly detection on the project flow chart; and a conversion module, configured to, in response to a normal detection result, convert the project flow chart into a project decision model based on a preset execution logic.

[0013] In a third aspect, an intelligent device is provided. The intelligent device includes at least one processor; and a memory communicatively connected to the at least one processor; wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method described in any one of the technical solutions of the above zero-code visualization AI algorithm orchestration method is implemented.

[0014] In a fourth aspect, a computer-readable storage medium is provided. A plurality of program codes are stored in the computer-readable storage medium, and the program codes are suitable for being loaded and run by a processor to execute the method described in any one of the technical solutions of the above zero-code visualization AI algorithm orchestration method.

[0015] One or more of the above technical solutions of the present application have at least one or more of the following beneficial effects:

[0016] In implementing the technical solution of the present application, users can combine resource nodes on the visualization canvas to transform the abstract process into an intuitive project flow chart, where the resource nodes are used to provide data sources, AI algorithm services, and logical rules. By obtaining the project flow chart created by the user and performing anomaly detection on it, when the detection result is normal, the project flow chart is converted into a project decision-making model according to the preset execution logic. The purpose of zero-code AI algorithm orchestration and simple and rapid project customization development is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Referring to the accompanying drawings, the disclosure of the present application will become more readily understood. It is easily understood by those skilled in the art that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present application. Among them:

[0018] Figure 1 is a schematic diagram of the main steps of the zero-code visualization AI algorithm orchestration method according to an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of a project flow according to an embodiment of the present application;

[0020] Figure 3a is a schematic diagram of a project flow according to another embodiment of the present application;

[0021] Figure 3b is a schematic diagram of a first matrix according to an embodiment of the present application;

[0022] Figure 3c is a schematic diagram of an inverted matrix according to an embodiment of the present application;

[0023] Figure 3d is a schematic diagram of a second matrix according to an embodiment of the present application;

[0024] Figure 4 is a schematic diagram of the main structural block diagram of the zero-code visualization AI algorithm orchestration system according to an embodiment of the present application;

[0025] Figure 5a is a schematic diagram of the system interface according to an embodiment of the present application;

[0026] Figure 5b is a schematic diagram of the spatio-temporal constraint node parameters according to an embodiment of the present application;

[0027] Figure 5c is a schematic diagram of the video frame extraction node parameters according to an embodiment of the present application;

[0028] Figure 6 is a schematic diagram of the main structure of an intelligent device according to an embodiment of the present application.

[0029] Reference numerals:

[0030] 11: Memory; 12: Processor. Detailed implementation manners

[0031] Some implementation manners of the present application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principle of the present application and are not intended to limit the protection scope of the present application.

[0032] In the description of the present application, the terms "first", "second", etc. are used to distinguish similar objects and do not necessarily need to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The terms "mount", "connect", and "couple" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can also be the communication inside two components. It can be a wireless connection or a wired connection.

[0033] In addition, a "module" and a "processor" can include hardware, software, or a combination of both. A module can include a hardware circuit, various suitable sensors, communication ports, memory, and can also include a software part, such as program code, or a combination of software and hardware. A processor can be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor can be implemented in a software manner, a hardware manner, or a combination of both. A computer-readable storage medium includes any suitable medium that can store program code, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and so on.

[0034] In addition, if the meaning of "and / or" appears in this application, it includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, or solution B, or the solution where both A and B are satisfied simultaneously. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application. The term "at least one of A or B" or "at least one of A and B" has a meaning similar to "A and / or B" and can include only A, only B, or both A and B. The singular terms "a" and "this" can also include the plural form.

[0035] For the relevant user personal information that may be involved in each embodiment of this application, it is all processed in strict accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, based on reasonable purposes in the project scenario, for the personal information actively provided by the user during the use of the product / service or generated due to the use of the product / service, as well as the personal information obtained with the user's authorization.

[0036] The user personal information processed by this application will vary depending on the specific product / service scenario. It is subject to the specific scenario of the user's use of the product / service and may involve the user's account information, device information, driving information, vehicle information, or other relevant information. This application will treat the user's personal information and its processing with a high degree of diligence.

[0037] This application attaches great importance to the security of user personal information and has taken security protection measures that meet industry standards and are reasonable and feasible to protect the user's information and prevent personal information from being accessed, publicly disclosed, used, modified, damaged, or lost without authorization.

[0038] Generally, project development requires flexible combinations based on various AI algorithms. When facing different projects and different scenarios, the combination methods of algorithms also need to be correspondingly modified. Customized project development takes a long time and has a certain degree of operational difficulty. To address the above problems, this application provides a zero-code visualization AI algorithm orchestration method.

[0039] Refer to the appendix Figure 1 , Figure 1 which is a schematic diagram of the main step flow of the zero-code visualization AI algorithm orchestration method according to an embodiment of this application. As Figure 1 shown, this method mainly includes the following steps S2 to step S6:

[0040] Step S2, obtain the project flow chart created by the user based on the visualization canvas and resource nodes, where the resource nodes are used to provide data sources, AI algorithm services, and logical rules.

[0041] In this embodiment, the visualization canvas is a tool platform for realizing interactive design, data orchestration, or process modeling through a graphical interface. Users can complete the operation of creating a project flow chart by dragging and connecting preset resource nodes without coding, thereby reducing the user operation threshold and improving the project development efficiency. Among them, the resource nodes are used to provide data sources, AI algorithm services, and logical rules. The data source is the original data input relied on by the project during the planning, execution, and delivery processes, such as data in an enterprise database, publicly available datasets, real-time collected data, and so on; the AI algorithm service encapsulates artificial intelligence algorithms into reusable functional modules for users to call as resource nodes; the logical rules are used to further control the execution of the process or data. Exemplarily, the logical rules include, but are not limited to: imposing a duration, spatio-temporal constraints, conditional judgment on the AI algorithm, or setting the data processing method (such as the video frame extraction method).

[0042] In one embodiment, the visualization canvas is realized through the coordination of multiple technology stacks such as front-end interaction, graphics rendering, data orchestration, and back-end execution. For specific reference, the methods in the prior art can be referred to, and details are not described here again.

[0043] In one embodiment, the algorithm node (the resource node providing the AI algorithm service) can be a pre-trained artificial intelligence model for a certain application scenario, such as a personnel behavior detection model, a vehicle behavior detection model, a scene detection model, a visual question answering model, an alarm monitoring model, and so on. It can be understood that different artificial intelligence models can also be combined and used as a new resource node for users to call. For example, the personnel behavior detection model and the alarm monitoring model are combined to obtain a behavior detection and alarm model for users to call.

[0044] In one embodiment, for any problem that can be solved by a process composed of multiple algorithms and rules, the method in the embodiment of the present application can be used for processing.

[0045] In one embodiment, assume that the project needs to count the number of staff members who are making calls or smoking in a certain video segment. The project flow chart at this time is as Figure 2 shown. Among them, the data source is the video data to be counted, that is, personnel event data. For this data source, on the one hand, the call detection model (node) is used to identify the staff members making calls, and on the other hand, the smoking detection model is used to identify the smoking staff members. Then, the staff members making calls or smoking are obtained through the work uniform detection node, and finally, the number of staff members making calls or smoking is output through the visual large model.

[0046] It should be noted that the above project flow chart is obtained by the user dragging multiple resource nodes onto the visualization canvas and creating connection relationships for the multiple resource nodes. By different combinations of the resource nodes, customized development of various projects can be realized.

[0047] In one embodiment, the prerequisite for creating connection relationships for multiple resource nodes is that the modalities of any two resource nodes are aligned. Exemplarily, for instance, if the personnel event data is video data, then the input data of the call detection node and the smoking detection node connected thereto are both video data. Assuming that the outputs of the call detection node and the smoking detection node are picture data, then the input of the work uniform detection node is also picture data.

[0048] In one embodiment, when the user creates a project flow chart, when the modalities of the two resource nodes for which the connection relationship is created are not aligned, a first prompt message is generated. As an example, assume that node A is to be connected to node B, but the output of node A is a picture and the input of node B is text. At this time, the modalities of node A and node B are not aligned, and an error message indicating that the node modalities are not aligned can be prompted to the user.

[0049] Step S4, perform anomaly detection on the project flow chart.

[0050] In this embodiment, since the logic of the project flow chart created by the user is not necessarily accurate, in order to ensure the executability of the process, anomaly detection is performed on the project flow chart created by the user.

[0051] In one embodiment, the project flow chart includes at least one input node and at least one output node. Among them, the input node is the data source, and the output node can be selected according to requirements, such as using a vision large model, a large language model, etc. to output the desired result. It can be understood that for projects with multiple data sources or multiple output requirements, the input node and the output node can also be two or more, and multiple input nodes or multiple output nodes can be of different modalities. Exemplarily, assume that the project needs to generate a target picture that meets the text description based on a piece of text and an initial picture. Then the input node can include two nodes, namely text and the initial picture, and the output node is the target picture. Further, assume that now the labels and classifications corresponding to the target picture are to be generated. Then the above-mentioned target picture can be used as an intermediate to connect to two other text output nodes, which respectively output the labels and classifications corresponding to the target picture.

[0052] In an alternative embodiment, performing anomaly detection on the project flow chart includes: detecting whether there are abnormal situations such as islands, closed loops, no input nodes, or no output nodes in the project flow chart.

[0053] In this embodiment, in order to avoid problems such as process interruption, incorrect execution, and inability to terminate in the developed project, anomaly detection is performed on the project flow chart obtained in step S2, such as detecting whether there are abnormal situations such as islands, closed loops, no input nodes, or no output nodes in the flow chart.

[0054] In one embodiment, the project flow chart can be converted into a first matrix represented by resource nodes and the connection relationships between the resource nodes. Taking Figure 3a the shown project flow chart as an example, where A, B, C, and D represent multiple resource nodes, and the arrows represent the execution directions of the processes. Specifically, A→B means that A is executed first and then B, that is, node A is the pre - dependency of node B. For this project flow chart, it can be represented by the first matrix shown in Figure 3b . The first matrix is an n - order square matrix, and n represents the number of resource nodes in the project flow chart. Specifically, a unique index can be assigned to each node in the project flow chart (such as in alphabetical order), and then an n*n all - zero matrix X is created. The row index i and column index j of X ij correspond to the indexes of the nodes in the project flow chart. Any element X ij in the matrix X corresponds to the connection relationship (edge) between node i and node j. Traverse each edge in the project flow chart and set the corresponding element in matrix X to 1. Exemplarily, Figure 3a the edges in it include: A→B, B→C, D→C, B→D. Therefore, in the first matrix X, X AB = 1, X BC = 1, X DC = 1, X BD = 1. At this time, anomaly detection can be performed on the project flow chart based on the first matrix. For example, it can be determined whether there are isolated islands by judging whether there are nodes with both row sum and column sum equal to 0 in the first matrix.

[0055] It can be understood that in addition to the anomalies in the above - mentioned embodiments, anomaly detection can also be performed on the security, execution performance of the process, or whether it meets the preset project rules. This embodiment does not specifically limit the abnormal situations.

[0056] Step S6, in response to the normal detection result, convert the project flow chart into a project decision model based on the preset execution logic.

[0057] In this embodiment, when no abnormal situation is detected in step S4, that is, the detection result is normal, the project flow chart created by the user is converted into a project decision model based on the preset execution logic. Among them, the preset execution logic is used to convert the nodes in the project flow chart into multiple steps that are executed in sequence.

[0058] In one embodiment, taking Figure 3a the shown project flow chart as an example, the steps to convert the project flow chart created by the user into a project decision model based on the preset execution logic are as follows:

[0059] 1) First, find the "start node", that is, the node without pre - dependency (such as Figure 3a node A in it). For a computer, it can be found through the inverted matrix X of the first matrix XT (As shown in Figure 3c ), the row in which all elements are 0 determines the "start node". It should be noted that the introduction of the inverted matrix X T is to facilitate the unified operation of the matrix by the computer. Here, it is assumed that the computer traverses the matrix by row first.

[0060] 2) Then find the next node of the "start node". There is a one-way dependency between the next node and the previous node, that is, there is a one-way dependency between the row node and the column node of the element with a value of 1 in the inverted matrix X T . Based on this, from Figure 3c it can be determined that the next node of the "start node" (node A) is node B.

[0061] 3) And so on, continue to find the next node of node B. At this time, according to Figure 3c it is judged that both node C and D can be the next node of node B. At this time, the following execution logic can be adopted: If the current node has a one-way dependency with multiple nodes (is dependent on multiple nodes), skip the nodes that have not appeared before among the multiple nodes, and give priority to calculating the nodes that have not appeared before, and so on until the "end node" appears. The "end node" is the node without a post-dependency, corresponding to the row in which all elements of the first matrix X are 0, that is, node C. According to the above execution logic, nodes C and D have not appeared before, so nodes C and D are skipped. And because node C is the "end node", the execution order of the (resource) nodes in the project flow chart is A→B→D→C.

[0062] Then, according to the above node execution order arrangement algorithm, the arranged algorithm is encapsulated into a complete model, that is, the project decision-making model.

[0063] In one implementation, the project decision-making model can be converted into a second matrix represented by resource nodes and the execution order between resource nodes for storage. The execution order between resource nodes is determined by a preset execution logic. If the execution order of nodes is also represented by a matrix, the Figure 3d shown node execution matrix (second matrix) can be obtained. Where L1 to L4 represent steps 1 to 4. The element value of L1 at node A is 1, so node A is step 1, and so on. Steps 2, 3, and 4 correspond to nodes B, D, and C respectively.

[0064] In an alternative implementation, after step S6, the following steps S8 and S10 can be further included:

[0065] Step S8, in response to the user's query of the project flow chart, echo the project flow chart on the visualization canvas based on the first matrix.

[0066] In this embodiment, when the user wants to query the project flow chart created previously, the project flow chart is echoed on the visualization canvas based on the first matrix in the above embodiment, facilitating operations such as viewing or modification by the user.

[0067] Step S10, in response to the user invoking the intelligent decision-making model, each resource node is calculated based on the second matrix in the execution order.

[0068] In this embodiment, when the user wants to use the intelligent decision-making model obtained by orchestration, each resource node is calculated according to the stored second matrix in the execution order.

[0069] In one implementation, the intelligent decision-making model can be invoked through a pre-set API interface to calculate each resource node in the execution order, or the intelligent decision-making model can be invoked by creating a task to calculate each resource node in the execution order.

[0070] It should be noted that although the above embodiments describe the various steps in a specific order, those skilled in the art can understand that for the purpose of achieving the effects of this application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these adjusted solutions are equivalent technical solutions to the technical solutions described in this application, and thus will also fall within the protection scope of this application.

[0071] Another aspect of this application also provides a zero-code visualization AI algorithm orchestration system, as Figure 4 shown, including: an acquisition module 2, configured to acquire the project flow chart created by the user based on the visualization canvas and resource nodes, where the resource nodes are used to provide data sources, AI algorithm services, and logical rules; a detection module 4, configured to perform anomaly detection on the project flow chart; and a conversion module 6, configured to, in response to the detection result being normal, convert the project flow chart into a project decision-making model based on a preset execution logic.

[0072] The above zero-code visualization AI algorithm orchestration system is used to execute Figure 1 the zero-code visualization AI algorithm orchestration method embodiment shown. The technical principles, the technical problems solved, and the technical effects produced by the two are similar. Those skilled in the art of this technology can clearly understand that for the convenience and conciseness of description, the specific working process and related descriptions of the zero-code visualization AI algorithm orchestration system can refer to the content described in the embodiment of the zero-code visualization AI algorithm orchestration method, which will not be elaborated here.

[0073] In an alternative implementation, Figure 5aIt is a schematic diagram of the system interface. Specifically, users can build a project flow chart by dragging various resource nodes on the visual canvas. Among them, the resource nodes can provide data selection, algorithm selection, and rule selection. Data selection means selecting data sources, and one or more of video, audio, picture, and text can be selected as one or more input nodes of the project flow chart; algorithm selection provides various AI algorithm services, including vision models, language models, speech models (speech recognition models and speech synthesis models), etc.; rule selection includes limiting the algorithm duration, spatio-temporal constraints, conditional judgment, and data processing, etc.

[0074] In one implementation, the resource node can provide a parameter setting function. Exemplarily, refer to Figure 5b and Figure 5c 。 Figure 5b Shows the adjustable parameters of the spatio-temporal constraint node, including the settings of input modality and output modality, time interval (such as setting the first alarm time and the last alarm event), camera spatial distance, algorithm selection, and whether it takes effect (default to take effect). Through the above settings, the spatio-temporal constraints on the algorithm of the previous node can be achieved. Figure 5c Shows the adjustable parameters of video frame extraction, including the settings of input modality, output modality, video extraction logic, video extraction interval, and video extraction duration. It can be understood that in this embodiment, the resource node provides the setting of adjustable parameters, which can better meet the project requirements. In one implementation, the adjustable parameters of the resource node can be set by double-clicking the node.

[0075] After the project flow chart is completed, the user can click the confirmation button, and the project flow chart is converted into a node relationship matrix, that is, the first matrix, and the system judges whether there are abnormal situations (island judgment, loop judgment, data source judgment, output node judgment). After judging that there is no abnormal situation, the system calculates the execution order of the nodes based on the node relationship matrix and its transposed matrix, generates a node execution matrix (the second matrix) based on the calculated execution order, and persists the node relationship matrix and the node execution matrix for storage.

[0076] When the user queries a certain project process, the project flow chart can be echoed on the canvas based on the node relationship matrix; when the user wants to execute the project process, the process can be called by calling the API interface of the mode or an analysis task can be created through the task mode, and the system will calculate and execute each node in turn based on the node execution matrix. Optionally, the system also provides a project information window for displaying the basic information of the project.

[0077] The system can realize the combination of multiple AI algorithms, and the inheritance of new algorithms can be seamlessly connected, effectively reducing the operation threshold of users and improving the efficiency of project customization development.

[0078] Those skilled in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments of the present application can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc., that can carry the computer program code.

[0079] Another aspect of the present application also provides a computer-readable storage medium.

[0080] In an embodiment of a computer-readable storage medium according to the present application, the computer-readable storage medium can be configured to store a program for executing the zero-code visualization AI algorithm orchestration method of the above-mentioned method embodiment. This program can be loaded and run by a processor to implement the above-mentioned zero-code visualization AI algorithm orchestration method. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiments of the present application is a non-transitory computer-readable storage medium.

[0081] Another aspect of the present application also provides an intelligent device.

[0082] In an embodiment of an intelligent device according to the present application, the intelligent device can include at least one processor; and a memory communicatively connected to at least one processor; wherein, a computer program is stored in the memory, and when the computer program is executed by at least one processor, the method described in any of the above embodiments is implemented. The intelligent device described in the present application can include devices such as driving devices, intelligent vehicles, and robots. Refer to the appendix Figure 6 , Figure 6 In which, it is exemplarily shown that the memory 11 and the processor 12 are communicatively connected through a bus.

[0083] In some embodiments of the present application, the intelligent device may further include at least one sensor for sensing information. The sensor is communicatively connected to any type of processor mentioned in the present application. Optionally, the intelligent device described in the present application may be, but is not limited to, a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, a vehicle-mounted device, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), an augmented reality (AR) / virtual reality (VR) device, etc., and the embodiments of the present application do not limit this.

[0084] So far, the technical solution of the present application has been described in conjunction with one embodiment shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principle of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present application.

Claims

1. A zero-code visualization AI algorithm orchestration method, characterized in that, The method includes: Obtaining a project flow chart created by a user based on a visualization canvas and resource nodes, where the resource nodes are used to provide data sources, AI algorithm services, and logical rules; Performing anomaly detection on the project flow chart; In response to the detection result being normal, converting the project flow chart into a project decision model based on a preset execution logic.

2. The method according to claim 1, wherein: The project flow chart is obtained by the user dragging multiple resource nodes onto the visualization canvas and creating connection relationships for the multiple resource nodes, where the prerequisite for creating connection relationships for the multiple resource nodes is that the modalities of any two resource nodes are aligned.

3. The method according to claim 2, wherein The project flow chart includes at least one input node and at least one output node. The performing anomaly detection on the project flow chart includes: Detecting whether there are abnormal situations such as islands, closed loops, no input nodes, or no output nodes in the project flow chart.

4. The method according to claim 2, wherein The method further includes: Converting the project flow chart into a first matrix represented by resource nodes and connection relationships between resource nodes for storage.

5. The method according to claim 4, characterized in that, The method further includes: In response to the user querying the project flow chart, echoing the project flow chart on the visualization canvas based on the first matrix.

6. The method according to claim 1, wherein The method further includes: Converting the project decision model into a second matrix represented by resource nodes and the execution order between resource nodes for storage, where the execution order between resource nodes is determined by the preset execution logic.

7. The method according to claim 6, wherein The method further includes: In response to the user invoking the intelligent decision model, calculating each resource node based on the second matrix according to the execution order.

8. An AI algorithm orchestration system with zero-code visualization, characterized in that, The system includes: An obtaining module, configured to obtain a project flow chart created by a user based on a visualization canvas and resource nodes, where the resource nodes are used to provide data sources, AI algorithm services, and logical rules; A detecting module, configured to perform anomaly detection on the project flow chart; A converting module, configured to, in response to the detection result being normal, convert the project flow chart into a project decision model based on a preset execution logic.

9. An intelligent device, characterized in that, Including: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing multiple program codes, characterized in that, The program code is suitable for being loaded and run by a processor to execute the method according to any one of claims 1 to 7.

Images