A method and device for model selection using a subgraph execution engine

Abstract

The present application discloses a method for model selection using a subgraph execution engine, comprising: obtaining a model selection strategy corresponding to the task to be inferred, the model selection strategy being used to select a model for executing the task to be inferred, and the model selection strategy including at least one field and a judgment condition corresponding to at least one field. According to the dependency relationship between services pre-stored in the subgraph execution engine, the target service required to execute to obtain at least one field is determined. The target service is executed to obtain the value of at least one field. According to the value of at least one field and the model selection strategy, the target model for executing the task to be inferred is determined, and the target model is a large model or a small model. It can be seen that this solution can determine whether to use a large model or a small model to execute the task to be inferred based on the model selection strategy. This solution has no strict requirements on the output format of the small model. Therefore, this solution can select corresponding models for tasks to be inferred corresponding to various scenarios.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for performing model selection using a subgraph execution engine. Background Art

[0002] With the development of large models, more and more reasoning tasks can be implemented using large models. Large models can be, for example, large language models (LLM) or multimodal large language models (MLLM).

[0003] However, large language models and large multimodal language models consume significant resources for reasoning. Small models, on the other hand, consume relatively few resources for task reasoning. Therefore, it is crucial to utilize both large and small models appropriately for reasoning tasks.

[0004] How to reasonably use large models and small models to perform reasoning tasks is a problem that has yet to be solved. Summary of the Invention

[0005] In order to solve or at least partially solve the above technical problems, the present application provides a method and device for model selection using a subgraph execution engine.

[0006] In a first aspect, the present application provides a method for performing model selection using a subgraph execution engine, the method comprising:

[0007] Obtaining a model selection strategy corresponding to the task to be inferred, where the model selection strategy is used to select a model for executing the task to be inferred, and the model selection strategy includes at least one field and a judgment condition corresponding to the at least one field;

[0008] Determining a target service required to be executed to obtain the at least one field based on dependency relationships between services pre-stored in the subgraph execution engine;

[0009] executing the target service to obtain a value of the at least one field;

[0010] A target model for executing the task to be inferred is determined according to the value of the at least one field and the model selection strategy, where the target model is a large model or a small model.

[0011] Optionally, the dependency relationships between services pre-stored in the subgraph execution engine include:

[0012] At least one directed acyclic graph, each directed acyclic graph in the at least one directed acyclic graph is used to indicate a group of services with dependency relationships, wherein a node in the directed acyclic graph corresponds to a service, the direction of the edge between the nodes indicates the upstream and downstream relationship between the nodes, and the edge between the nodes also indicates the fields transferred between the nodes.

[0013] Optionally, determining the target service required to be executed to obtain the at least one field based on dependencies between services pre-stored in the subgraph execution engine includes:

[0014] For each field of the at least one field, determining a first service that generates the field, and searching for a target directed acyclic graph including the first service;

[0015] Determining the target service includes the first service in the target directed acyclic graph and a second service upstream of the first service.

[0016] Optionally, obtaining a model selection strategy corresponding to the task to be inferred includes:

[0017] The model selection strategy input by the user in the strategy configuration page provided by the strategy configuration platform is obtained.

[0018] Optionally, determining a target model for executing the task to be inferred based on the value of the at least one field and the model selection strategy includes:

[0019] Calling a strategy engine to judge the model selection strategy using the value of the at least one field, determining whether a judgment condition corresponding to the at least one field is satisfied, and obtaining a judgment result;

[0020] According to the judgment result, a target model for executing the task to be inferred is determined.

[0021] Optionally, the large model includes: a large language model or a multimodal large language model, and the small model includes other inference models except the large language model and the multimodal large language model.

[0022] In a second aspect, the present application provides a device for performing model selection using a subgraph execution engine, the device comprising:

[0023] an acquisition unit, configured to acquire a model selection strategy corresponding to the task to be inferred, wherein the model selection strategy is used to select a model for executing the task to be inferred, and the model selection strategy includes at least one field and a judgment condition corresponding to the at least one field;

[0024] A first determining unit is configured to determine a target service required to be executed to obtain the at least one field based on dependency relationships between services pre-stored in the subgraph execution engine;

[0025] an execution unit, configured to execute the target service to obtain a value of the at least one field;

[0026] The second determining unit is used to determine a target model for executing the task to be inferred based on the value of the at least one field and the model selection strategy, where the target model is a large model or a small model.

[0027] Optionally, the dependency relationships between services pre-stored in the subgraph execution engine include:

[0028] At least one directed acyclic graph, each directed acyclic graph in the at least one directed acyclic graph is used to indicate a group of services with dependency relationships, wherein a node in the directed acyclic graph corresponds to a service, the direction of the edge between the nodes indicates the upstream and downstream relationship between the nodes, and the edge between the nodes also indicates the fields transferred between the nodes.

[0029] Optionally, the first determining unit is configured to:

[0030] For each field of the at least one field, determining a first service that generates the field, and searching for a target directed acyclic graph including the first service;

[0031] Determining the target service includes the first service in the target directed acyclic graph and a second service upstream of the first service.

[0032] Optionally, the acquiring unit is configured to:

[0033] The model selection strategy input by the user in the strategy configuration page provided by the strategy configuration platform is obtained.

[0034] Optionally, the second determining unit is configured to:

[0035] Calling a strategy engine to judge the model selection strategy using the value of the at least one field, determining whether a judgment condition corresponding to the at least one field is satisfied, and obtaining a judgment result;

[0036] According to the judgment result, a target model for executing the task to be inferred is determined.

[0037] Optionally, the large model includes: a large language model or a multimodal large language model, and the small model includes other inference models except the large language model and the multimodal large language model.

[0038] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising a processor and a memory;

[0039] The processor is configured to execute instructions stored in the memory, so that the device performs the method as described in any one of the first aspects above.

[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions, wherein the instructions instruct a device to execute a method as described in any one of the above first aspects.

[0041] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a computer, enables the computer to execute any of the methods described in the first aspect above.

[0042] Compared with the prior art, the embodiments of the present application have the following advantages:

[0043] The present application provides a method for model selection using a subgraph execution engine, the method comprising: obtaining a model selection strategy corresponding to a task to be inferred, the model selection strategy being used to select a model for executing the task to be inferred, the model selection strategy comprising at least one field and a judgment condition corresponding to the at least one field. Furthermore, based on the dependency relationship between services pre-stored in the subgraph execution engine, a target service required to execute to obtain the at least one field is determined. After determining the target service, the target service can be further executed to obtain the value of the at least one field. And based on the value of the at least one field and the model selection strategy, a target model for executing the task to be inferred is determined, the target model being a large model or a small model. Thus, by using this solution, it is possible to determine whether to use a large model or a small model to execute the task to be inferred based on the model selection strategy, thereby reasonably utilizing the large model or the small model to execute the task to be inferred. This solution has no strict requirements on the output format of the small model. Therefore, this solution can select corresponding models for tasks to be inferred corresponding to various scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A flowchart of a method for selecting a model using a subgraph execution engine provided in an embodiment of the present application;

[0046] Figure 2 A schematic diagram of a process of a method for performing model selection using a subgraph execution engine provided in an embodiment of the present application;

[0047] Figure 3 A schematic diagram of a process of another method for performing model selection using a subgraph execution engine provided in an embodiment of the present application;

[0048] Figure 4 A schematic diagram of the structure of a device for performing model selection using a subgraph execution engine provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0050] The inventors of this application have found through research that, in order to reduce the resources consumed by executing reasoning tasks, it is hoped that small models can be used to execute reasoning tasks as much as possible. However, not all reasoning tasks can be executed using small models, because for some complex tasks, the reasoning results of small models may not be accurate. Therefore, in some scenarios:

[0051] A stone-throwing sampling approach can be used to determine whether a small model can be used to perform an inference task. Specifically, the small model can be used to generate a draft token for the inference task. The large model can then be used to determine whether the draft token is acceptable. If the large model determines that the draft token is acceptable, the inference result for the inference task is generated based on the draft token. If the large model determines that the draft token is not acceptable, the large model is selected to perform the inference task.

[0052] However, this approach requires the small model to output tokens that can be used to generate inference results for reasoning tasks, meaning it must be a generative model. In practice, however, small models are not limited to generative models. Therefore, the stone-throwing sampling approach is not suitable for all scenarios.

[0053] In view of this, the present application provides a method and device for model selection using a subgraph execution engine, which has no strict requirements on the output format of the small model and can select corresponding models for tasks to be inferred corresponding to various scenarios.

[0054] Various non-limiting embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0055] Exemplary Methods

[0056] See also Figure 1 , which is a flow chart of a method for model selection using a subgraph execution engine provided in an embodiment of the present application. The solution provided in an embodiment of the present application can be applied to a client or a server. As a specific example, the method can be applied to a subgraph execution engine deployed in a client or a server.

[0057] In this embodiment, the method may include the following steps: S101-S104.

[0058] S101: Obtain a model selection strategy corresponding to a task to be inferred, where the model selection strategy is used to select a model for executing the task to be inferred. The model selection strategy includes at least one field and a judgment condition corresponding to the at least one field.

[0059] In an embodiment of the present application, the model selection strategy may be a strategy set by a user for the task to be inferred, and the model selection strategy is used to select a model to perform the task to be inferred. In other words, the model selection strategy is used to determine whether to use a large model or a small model to perform the task to be inferred.

[0060] In the embodiments of the present application, the large model can be a large language model or a multimodal large language model, and the small language model is a model other than the large language model and the multimodal large language model. The embodiments of the present application do not specifically limit the type of the small model. The small model can be a classification model, a generative model, or other types of models, which are not listed here.

[0061] In one example, the model selection strategy may be input by a user through a human-computer interaction interface.

[0062] In another example, the model selection strategy may be input by the user on a strategy configuration page provided by the strategy configuration platform. In one example, the strategy configuration page may include a strategy input area in which the user may input the model selection strategy. The user may input the corresponding model selection strategy on the strategy configuration page according to their needs.

[0063] In an embodiment of the present application, the model selection strategy includes at least one field and a judgment condition corresponding to the at least one field. The judgment condition corresponding to the at least one field may include one or more sub-conditions, and a sub-condition may be associated with one or more fields of the at least one field. The judgment condition corresponding to the at least one field may be, for example, a condition that needs to be satisfied when executing the task to be inferred using a large model, or a condition that needs to be satisfied when executing the task to be inferred using a small model. This embodiment of the present application does not specifically limit this.

[0064] Regarding the fields included in the model selection strategy, they may be related to the task to be inferred or to the load of the large model (such as the calling frequency), and the embodiments of this application do not make specific limitations.

[0065] S102: Determine a target service required to be executed to obtain the at least one field based on dependency relationships between services pre-stored in the subgraph execution engine.

[0066] In the embodiment of the present application, the subgraph execution engine may pre-store the dependency relationship between services. Wherein, a service refers to a functional module that can implement a specific function. For example:

[0067] For the product library service, the service can output fields such as product title, product image, and product attributes based on the input product identifier (ID).

[0068] The word segmentation service can segment the input sentence into words. The word segmentation service can segment the product title into corresponding words.

[0069] For the image recognition service, it can process the input image and identify the subject included in the image. The image recognition service can process the product image and identify the subject in the image.

[0070] For the keyword recognition service, it can perform keyword recognition on the input word segmentation and output the recognized keywords.

[0071] In an embodiment of the present application, the subgraph execution engine may store the identifiers of each service and the input and output fields of each service, which may be used to determine dependencies between services.

[0072] The so-called dependency relationship between services may include the association relationship between services. For a service, the services with which it has an association relationship may include its upstream services and / or its downstream services. The dependency relationship between services also includes the fields passed between services. The fields passed between services refer to the fields output by the upstream service to its directly associated downstream service. Regarding the dependency relationship between services, let's take an example: Service A outputs Field 1 to Service B, and Service B outputs Field 2 to Service C. In this scenario, Service A is the upstream service of Service B, and Service B is the upstream service of Service C. The field passed by Service A to Service B is Field 1, and the field passed by Service B to Service C is Field 2.

[0073] In a specific example, the dependency relationship between the aforementioned services can be reflected as at least one directed acyclic graph (DAG). Each DAG in the at least one DAG is used to indicate a group of services with a dependency relationship, wherein, for each DAG, it can include multiple nodes, and the edges between the multiple nodes are directed edges. The direction of the directed edge is used to indicate the upstream and downstream relationship between the nodes. Specifically, the directed edge can be directed from the upstream node to the downstream node, the upstream node corresponds to the upstream service, and the downstream node corresponds to the downstream service. In addition, the directed edge can also indicate the fields transferred between nodes, wherein the fields transferred between nodes can be used as attributes of the directed edge. Regarding the DAG, it is now explained with reference to the aforementioned service A outputting field 1 to service B, service B outputting field 2 to service C, and service C outputting field 3 as an example. In this scenario:

[0074] A DAG can include three nodes, one for each service: Service A, Service B, and Service C. There is a directed edge between the node corresponding to Service A and the node corresponding to Service B. This directed edge points from the node corresponding to Service A to the node corresponding to Service B. This directed edge also has attribute 1, which indicates that the field pointed to by Service A at Service B is Field 1. There is also a directed edge between the node corresponding to Service B and the node corresponding to Service C. This directed edge points from the node corresponding to Service B to the node corresponding to Service C. This directed edge also has attribute 2, which indicates that the field pointed to by Service B at Service C is Field 2.

[0075] In the embodiment of the present application, when S102 is specifically implemented, the method of determining the service required to be executed for each field in the at least one field is the same. Accordingly, the aforementioned target service may include the service required to be executed for each field in the at least one field.

[0076] For the convenience of description, any one of the at least one field is referred to as a "target field". Next, a method for determining the service required to be executed to obtain the target field is described.

[0077] In one example, the target field can be used as an index to first search for a first service that outputs the target field. Furthermore, based on the dependency relationship between the aforementioned services, at least one second service upstream of the first service is determined. The second service upstream of the first service mentioned here may include a service that directly passes the corresponding field to the first service (i.e., the direct upstream service of the first service). If the upstream service of the first service also has an upstream service, the second service also includes the upstream service of the upstream service of the first service. After determining the first service and the second service, it can be determined that the services required to obtain the target field include the first service and the second service. In an example, if the first service does not include an upstream service, the services required to obtain the target field may only include the first service.

[0078] In the scenario where the dependency between services is embodied as a DAG, when S102 is specifically implemented, it is possible to first use the target field as an index to search for the first service that outputs the target field. Further, the target DAG including the first service is searched, for example, using the first service as an index, multiple pre-stored DAGs are queried to obtain the target DAG including the first service. In the present application, the target DAG includes the first service, which can be understood as the target service including the node corresponding to the first service. After determining the target DAG, the first service in the target DAG and the second service upstream of the first service can be determined as the services required to be executed to obtain the target field. Of course, the target DAG may also include only one node (i.e., the node corresponding to the first service). In this scenario, the services required to be executed to obtain the target field only include the first service.

[0079] S103: Execute the target service to obtain the value of the at least one field.

[0080] After determining the target service, the target service can be executed to obtain the value of the at least one field. Specifically, for each of the at least one field, the service required to obtain the field can be executed separately to obtain the value of the field. Taking the target field as an example, in a scenario where the service required to obtain the target field only includes the first service, the first service can be executed to obtain the value of the target field. In a scenario where the service required to obtain the target field includes the first service and the second service, the first service and the second service can be executed in the order of first executing the upstream service and then executing the downstream service to obtain the value of the target field.

[0081] In scenarios where the dependencies between services are represented by a DAG, S103 can be implemented, for example, by executing the target DAG to obtain the value of the target field. Executing the target DAG means sequentially executing the services in the target DAG according to the upstream and downstream relationships between the services indicated by the target DAG. Of course, when executing the target DAG, execution may stop at the first service and bypass its downstream services, thereby saving computing resources.

[0082] S104: Determine a target model for executing the task to be inferred based on the value of the at least one field and the model selection strategy, where the target model is a large model or a small model.

[0083] After obtaining the value of the at least one field, the model selection strategy can be judged based on the value of the at least one field to determine whether the judgment condition corresponding to the at least one field is satisfied, thereby obtaining a judgment result. In a specific example, the aforementioned policy configuration platform can be associated with a policy engine, and the subgraph execution engine can include the policy engine. Accordingly, in the specific implementation of S104, the policy engine can be called to use the value of the at least one field to judge the model selection strategy, determine whether the judgment condition corresponding to the at least one field is satisfied, and obtain a judgment result.

[0084] Furthermore, the target model for executing the task to be inferred can be determined based on the judgment result. For example, when the aforementioned judgment condition is the condition that needs to be met for executing the task to be inferred using a large model, if the judgment result indicates that the judgment condition corresponding to the at least one field is satisfied, then the target model for executing the task to be inferred can be determined to be a large model; if the judgment result indicates that the judgment condition corresponding to the at least one field is not satisfied, then the target model for executing the task to be inferred can be determined to be a small model. Similarly, when the aforementioned judgment condition is the condition that needs to be met for executing the task to be inferred using a small model, if the judgment result indicates that the judgment condition corresponding to the at least one field is satisfied, then the target model for executing the task to be inferred can be determined to be a small model; if the judgment result indicates that the judgment condition corresponding to the at least one field is not satisfied, then the target model for executing the task to be inferred can be determined to be a large model.

[0085] From the above description, it can be seen that using this solution, it is possible to determine whether to use a large model or a small model to perform the task to be inferred based on the model selection strategy, so as to reasonably use the large model or the small model to perform the task to be inferred. This solution has no strict requirements on the output format of the small model. Therefore, this solution can select corresponding models for the tasks to be inferred corresponding to various scenarios, so that in various application scenarios, large models or small models can be reasonably used to perform the tasks to be inferred.

[0086] The above describes the solution provided by the embodiment of the present application. Figure 2 and Figure 3 , and then introduce the solution provided by the embodiment of this application. Among them, Figure 2 A schematic diagram showing a process of a method for model selection using a subgraph execution engine is shown. Figure 3 This figure is a process diagram of a method for using a subgraph execution engine to select a model for the inference task of "predicting product categories."

[0087] like Figure 2 As shown, the subgraph execution engine includes a policy engine, which corresponds to a policy configuration platform. Users can configure model selection strategies on the policy configuration platform, such as Figure 2 As shown:

[0088] The model selection strategy involves fields 1 and 2. Figure 3 As shown in the figure, for the "predict product category" inference task, Field 1 is the product title, and Field 2 is the image body. The subgraph execution engine obtains the model selection policy from the policy engine and, based on at least one pre-saved DAG, obtains the services required to obtain Fields 1 and 2.

[0089] like Figure 2 As shown, obtaining field 1 requires executing services X1 and X. Service X1 is the upstream service of service X, and field 1 is the output field of service X. By executing services X1 and X in sequence, the value of field 1 can be obtained. In the "predict product category" inference task, service X1 is the product library service, and service X is the word segmentation service. For details about the product library service and word segmentation service, please refer to the previous section and will not be repeated here.

[0090] Obtaining Field 2 requires executing Service Y1 and Service Y. Service Y1 is the upstream service of Service Y, and Field 2 is the field output by Service Y. By executing Service Y1 and Service Y sequentially, the value of Field 2 can be obtained. In the "predict product category" inference task, Service Y1 is the product library service, and Service Y is the image recognition service. For details about the image recognition service, please refer to the previous section and will not be repeated here.

[0091] After obtaining the values ​​of Field 1 and Field 2, the strategy engine can be called to judge the model selection strategy based on the values ​​of Field 1 and Field 2 to obtain the judgment result. Figure 2 In the example, the model selection strategy is explained by taking the case where field 1 meets condition A and field 2 meets condition B, and first judging whether field 1 meets condition A, and only when field 1 does not meet condition A will it be judged whether field 2 meets condition B. However, Figure 2It is only shown to facilitate understanding of this solution and does not constitute a limitation on the embodiments of the present application.

[0092] The present embodiment does not specifically limit the field 1 to satisfying condition A. In one example, field 1 satisfying condition A may include, for example, more than 10 word segments. The present embodiment does not specifically limit the field 2 to satisfying condition B. In one example, field 2 satisfying condition B may include, for example, more than 3 entities.

[0093] After obtaining the judgment result, based on the judgment result, it is determined whether the model performing the task to be inferred is a large model or a small model.

[0094] It should be noted that for Figure 2 In the solution shown, users can adjust the model selection policy through the policy configuration platform. For example, in one example, a user adjusts the model selection policy through the policy platform to introduce a new field 3. In this scenario, the subgraph execution engine can combine pre-stored dependencies between services to determine the service required to execute to obtain field 3.

[0095] like Figure 2 As shown, to obtain field 3, you need to execute service Z1 and service Z. Service Z1 is the upstream service of service Z, and field 3 is the field output by service Z. By executing service Z1 and service Z in sequence, you can get the value of field 3 (corresponding to Figure 2 The dotted part in the figure is provided as input to the strategy engine for judgment. In the task of "predicting product categories" to be inferred, field 3 is the keyword, service Z1 is the product library service, and service Z is the keyword recognition service. Regarding the keyword recognition service, please refer to the relevant description above and will not be repeated here. Accordingly, the judgment condition corresponding to field 3 can be, for example, that the keyword output by field 3 includes "women's clothing". For example, when the keyword corresponding to field 3 includes "women's clothing", the target model is determined to be the large model.

[0096] In this application, the newly added field 3 and the judgment conditions corresponding to field 3 can take effect immediately without modifying the software code logic related to model selection. This ensures the flexibility and convenience of model selection strategy configuration.

[0097] In summary, the solution provided by the embodiment of the present application has high flexibility and convenience for adjusting the fields and judgment conditions involved in the model selection strategy, and can easily and quickly reduce the frequency of using large models in reasoning tasks. In addition, this solution has no special requirements for the fields involved in the model selection strategy and the judgment conditions corresponding to the fields. Users can set them as needed, and it is highly scalable. For example, in addition to Figure 3In addition to the examples shown, the model selection strategy can also involve fields such as product type. For type 1 (e.g., women's clothing), a large model is used, and for type 2 (e.g., non-women's clothing), a small model is used. Another example is the frequency of use of the large model. If the frequency of use exceeds a certain threshold, such as a query rate per second (QPS) greater than 100, a small model is used; if the QPS is less than or equal to 100, a small model is used, and so on. These are not listed here one by one.

[0098] Exemplary devices

[0099] Based on the method provided in the above embodiment, the embodiment of the present application further provides a device, which is described below in conjunction with the accompanying drawings.

[0100] See also Figure 4 , Figure 4 A schematic diagram of the structure of a device for performing model selection using a subgraph execution engine provided in an embodiment of the present application.

[0101] Figure 4 The device 400 for performing model selection using a subgraph execution engine shown can be used to execute the method for performing model selection using a subgraph execution engine provided in the above method embodiment.

[0102] The apparatus 400 may specifically include, for example: an acquiring unit 401 , a first determining unit 402 , an executing unit 403 , and a second determining unit 404 .

[0103] An acquisition unit 401 is configured to acquire a model selection strategy corresponding to a task to be inferred, wherein the model selection strategy is used to select a model for executing the task to be inferred, and the model selection strategy includes at least one field and a judgment condition corresponding to the at least one field.

[0104] A first determining unit 402 is configured to determine a target service required to be executed to obtain the at least one field based on dependencies between services pre-stored in the subgraph execution engine;

[0105] An execution unit 403 is configured to execute the target service to obtain a value of the at least one field;

[0106] The second determining unit 404 is configured to determine a target model for executing the task to be inferred based on the value of the at least one field and the model selection strategy, where the target model is a large model or a small model.

[0107] Optionally, the dependency relationships between services pre-stored in the subgraph execution engine include:

[0108] At least one directed acyclic graph, each directed acyclic graph in the at least one directed acyclic graph is used to indicate a group of services with dependency relationships, wherein a node in the directed acyclic graph corresponds to a service, the direction of the edge between the nodes indicates the upstream and downstream relationship between the nodes, and the edge between the nodes also indicates the fields transferred between the nodes.

[0109] Optionally, the first determining unit 402 is configured to:

[0110] For each field of the at least one field, determining a first service that generates the field, and searching for a target directed acyclic graph including the first service;

[0111] Determining the target service includes the first service in the target directed acyclic graph and a second service upstream of the first service.

[0112] Optionally, the acquiring unit 401 is configured to:

[0113] The model selection strategy input by the user in the strategy configuration page provided by the strategy configuration platform is obtained.

[0114] Optionally, the second determining unit 404 is configured to:

[0115] Calling a strategy engine to judge the model selection strategy using the value of the at least one field, determining whether a judgment condition corresponding to the at least one field is satisfied, and obtaining a judgment result;

[0116] According to the judgment result, a target model for executing the task to be inferred is determined.

[0117] Optionally, the large model includes: a large language model or a multimodal large language model, and the small model includes other inference models except the large language model and the multimodal large language model.

[0118] Since the device 400 is a device corresponding to the method for using a subgraph execution engine to select a model provided in the above method embodiment, the specific implementation of each unit of the device 400 is based on the same concept as the above method embodiment. Therefore, regarding the specific implementation of each unit of the device 400, please refer to the relevant description part of the above method embodiment, which will not be repeated here.

[0119] An embodiment of the present application further provides an electronic device, the electronic device comprising a processor and a memory;

[0120] The processor is configured to execute instructions stored in the memory, so that the device executes the method for performing model selection using a subgraph execution engine provided in the above method embodiment.

[0121] An embodiment of the present application provides a computer-readable storage medium including instructions, wherein the instructions instruct a device to execute the method for performing model selection using a subgraph execution engine provided in the above method embodiment.

[0122] An embodiment of the present application further provides a computer program product, which, when executed on a computer, enables the computer to execute the method for performing model selection using a subgraph execution engine provided in the above method embodiment.

[0123] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0124] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

[0125] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for model selection using a subgraph execution engine, characterized in that: The method comprises: Obtaining a model selection strategy corresponding to the task to be inferred, the model selection strategy being used to select a model for executing the task to be inferred, the model selection strategy including at least one field and a judgment condition corresponding to the at least one field, wherein the task to be inferred is to predict a product category; According to the dependency relationship between services pre-stored in the subgraph execution engine, a target service required to be executed to obtain the at least one field is determined, wherein the dependency relationship between services includes the association relationship between services and the fields transferred between services, and the dependency relationship between services includes: the dependency relationship between the product library service, the word segmentation service, the image recognition service and the keyword recognition service, wherein the product library service is used to determine the product title, product image and product attributes based on the product identifier, the word segmentation service is used to segment sentences, the image recognition service is used to identify the subject included in the image, and the keyword recognition service is used to perform keyword recognition on the segmented words, and the target service includes: the product library service, the word segmentation service, the image recognition service and the keyword recognition service; executing the target service to obtain a value of the at least one field; A target model for executing the task to be inferred is determined according to the value of the at least one field and the model selection strategy, where the target model is a large model or a small model.

2. The method according to claim 1, characterized in that The dependency relationships between services pre-stored in the subgraph execution engine include: At least one directed acyclic graph, each directed acyclic graph in the at least one directed acyclic graph is used to indicate a group of services with dependency relationships, wherein a node in the directed acyclic graph corresponds to a service, the direction of the edge between the nodes indicates the upstream and downstream relationship between the nodes, and the edge between the nodes also indicates the fields transferred between the nodes.

3. The method according to claim 2, characterized in that The determining, based on the dependency relationship between services pre-stored in the subgraph execution engine, the target service required to be executed to obtain the at least one field includes: For each field of the at least one field, determining a first service that generates the field, and searching for a target directed acyclic graph including the first service; Determining the target service includes the first service in the target directed acyclic graph and a second service upstream of the first service.

4. The method according to claim 1, wherein The obtaining of the model selection strategy corresponding to the task to be inferred includes: The model selection strategy input by the user in the strategy configuration page provided by the strategy configuration platform is obtained.

5. The method according to claim 4, characterized in that The determining, based on the value of the at least one field and the model selection strategy, a target model for executing the task to be inferred includes: Calling a strategy engine to judge the model selection strategy using the value of the at least one field, determining whether a judgment condition corresponding to the at least one field is satisfied, and obtaining a judgment result; According to the judgment result, a target model for executing the task to be inferred is determined.

6. The method according to any one of claims 1 to 5, characterized in that The large model includes: a large language model or a multimodal large language model, and the small model includes other inference models except the large language model and the multimodal large language model.

7. A device for model selection using a subgraph execution engine, characterized in that: The device comprises: an acquisition unit, configured to acquire a model selection strategy corresponding to a task to be inferred, the model selection strategy being used to select a model for performing the task to be inferred, the model selection strategy comprising at least one field and a judgment condition corresponding to the at least one field, wherein the task to be inferred is predicting a product category; A first determining unit is configured to determine a target service required to be executed to obtain the at least one field based on dependency relationships between services pre-stored in a subgraph execution engine, wherein the dependency relationships between services include association relationships between services and fields transferred between services, and the dependency relationships between services include: dependency relationships between a product library service, a word segmentation service, an image recognition service, and a keyword recognition service, wherein the product library service is configured to determine a product title, a product image, and product attributes based on a product identifier, the word segmentation service is configured to segment sentences, the image recognition service is configured to identify subjects included in images, and the keyword recognition service is configured to perform keyword recognition on segmented words, and the target services include: the product library service, the word segmentation service, the image recognition service, and the keyword recognition service; an execution unit, configured to execute the target service to obtain a value of the at least one field; The second determining unit is used to determine a target model for executing the task to be inferred based on the value of the at least one field and the model selection strategy, where the target model is a large model or a small model.

8. The device according to claim 7, characterized in that The dependency relationships between services pre-stored in the subgraph execution engine include: At least one directed acyclic graph, each directed acyclic graph in the at least one directed acyclic graph is used to indicate a group of services with dependency relationships, wherein a node in the directed acyclic graph corresponds to a service, the direction of the edge between the nodes indicates the upstream and downstream relationship between the nodes, and the edge between the nodes also indicates the fields transferred between the nodes.

9. An electronic device, characterized in that: The device includes a processor and a memory; The processor is configured to execute instructions stored in the memory, so that the device executes the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that The method comprises instructions for instructing a device to execute the method according to any one of claims 1 to 6.

Images