A service request decision-making method, apparatus and equipment

Abstract

This application discloses a service request decision-making method, apparatus, and device to improve the flexibility of service request decision-making. First, static characteristics of the client are determined based on the service request. Then, a decision corresponding to the service request is obtained, which includes static decision conditions, a first dynamic decision condition, and the logical relationships between the decision conditions. Based on the matching result between the client's static characteristics and the static decision conditions, and the logical relationships between the decision conditions, the decision is simplified to generate a simplified decision. If the simplified decision includes at least one second dynamic decision condition, the simplified decision is sent to the client, so that the client can generate a decision result indicating whether or not the service request can be responded to based on the client's dynamic characteristics and the second dynamic decision condition.

Description

Technical Field

[0001] This application relates to the field of Internet technology, specifically to a service request decision-making method, apparatus, and device. Background Technology

[0002] In internet applications, clients send service requests to servers, seeking a response to a specific service. Due to client performance limitations, servers make decisions to determine whether the client can respond to the service request. Currently, servers typically make these decisions based on static client characteristics; however, this approach lacks flexibility and fails to fully utilize client performance. Summary of the Invention

[0003] In view of this, embodiments of this application provide a service request decision-making method, apparatus, and device to improve the flexibility of service request decision-making.

[0004] To address the above problems, the technical solutions provided in this application are as follows:

[0005] In a first aspect, embodiments of this application provide a service request decision method, the method comprising:

[0006] Receive service requests sent by clients and determine client static characteristics based on the service requests;

[0007] Obtain the decision corresponding to the service request, the decision including decision conditions and the logical relationship between the decision conditions; the decision conditions include static decision conditions and a first dynamic decision condition;

[0008] Based on the matching results between the client's static features and the static decision conditions, as well as the logical relationship between the decision conditions, the decision is simplified to generate a simplified decision.

[0009] If the simplified decision includes a second dynamic decision condition, the simplified decision is sent to the client so that the client generates a decision result indicating whether the service request can be responded to based on the matching result between the client's dynamic characteristics and the second dynamic decision condition.

[0010] If the simplified decision includes multiple second dynamic decision conditions and the logical relationship between the second dynamic decision conditions, the simplified decision is sent to the client so that the client generates a decision result indicating whether the service request can be responded to based on the matching result of the client's dynamic characteristics with the second dynamic decision conditions and the logical relationship between the second dynamic decision conditions.

[0011] The second dynamic decision condition is at least one of the first dynamic decision conditions.

[0012] Secondly, embodiments of this application provide a service request decision-making apparatus, the apparatus comprising:

[0013] A determining unit is used to receive a service request sent by a client and determine the client's static characteristics through the service request.

[0014] The first acquisition unit is used to acquire the decision corresponding to the service request, the decision including decision conditions and the logical relationship between the decision conditions; the decision conditions include static decision conditions and a first dynamic decision condition.

[0015] The generation unit is used to simplify the decision based on the matching result between the client's static features and the static decision conditions, as well as the logical relationship between the decision conditions, and generate a simplified decision.

[0016] The first sending unit is configured to send the simplified decision to the client if the simplified decision includes a second dynamic decision condition, so that the client generates a decision result indicating whether the service request can be responded to based on the matching result between the client's dynamic characteristics and the second dynamic decision condition.

[0017] The second sending unit is configured to send the simplified decision to the client if the simplified decision includes multiple second dynamic decision conditions and the logical relationship between the second dynamic decision conditions, so that the client generates a decision result indicating whether the service request can be responded to based on the matching result of the client's dynamic characteristics and the second dynamic decision conditions, and the logical relationship between the second dynamic decision conditions.

[0018] The second dynamic decision condition is at least one of the first dynamic decision conditions.

[0019] Thirdly, embodiments of this application provide a service request decision-making device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the service request decision-making method as described above.

[0020] Fourthly, embodiments of this application provide a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to perform the service request decision method described above.

[0021] Therefore, the embodiments of this application have the following beneficial effects:

[0022] In this embodiment, upon receiving a service request from a client, the system first determines the client's static characteristics based on the service request. Then, it obtains the decision corresponding to the service request, which includes static decision conditions, a first dynamic decision condition, and the logical relationships between these decision conditions. Based on the matching result between the client's static characteristics and the static decision conditions, and the logical relationships between the decision conditions, the decision is simplified to generate a simplified decision. If the simplified decision includes at least one second dynamic decision condition, the simplified decision is sent to the client, enabling the client to generate a decision indicating whether or not to respond to the service request based on the client's dynamic characteristics and the second dynamic decision condition. This approach integrates the client's fixed static characteristics and its real-time changing dynamic characteristics during the decision generation process, thereby fully utilizing the client's performance and improving the flexibility of service request decision-making. Attached Figure Description

[0023] Figure 1 A schematic diagram illustrating an exemplary application scenario provided in this application embodiment;

[0024] Figure 2 A flowchart illustrating a service request decision-making method provided in this application embodiment;

[0025] Figure 3 A flowchart for generating a simplified decision-making process is provided as an embodiment of this application;

[0026] Figure 4 A schematic diagram illustrating the generation of simplified decisions, provided as an embodiment of this application;

[0027] Figure 5 This is a schematic diagram illustrating another method for generating simplified decisions, provided as an embodiment of this application.

[0028] Figure 6 A schematic diagram of a service request decision-making device provided in an embodiment of this application;

[0029] Figure 7 This is a schematic diagram of a device provided in an embodiment of this application. Detailed Implementation

[0030] To make the above-mentioned objectives, features and advantages of the embodiments of this application more apparent and understandable, the embodiments of this application will be further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0031] To facilitate understanding and explanation of the technical solutions provided in the embodiments of this application, the background technology of the embodiments of this application will be described first below.

[0032] In internet applications, clients send service requests to servers in exchange for a specific service. For example, a client might request to record at the highest recording resolution or to play a video at the highest playback resolution. Due to client performance limitations, the server will assess the service request to determine whether the client is capable of responding to it.

[0033] Currently, servers typically make decisions based on static client characteristics. For example, the server may pre-set a mapping between device models and supported recording resolutions, allowing recording at the highest resolution only when the client is on a high-end device. However, client states are constantly changing. For instance, even high-end devices may experience stuttering when recording at the highest resolution under heavy processor load; conversely, low-end devices with light processor load and minimal background activity can record smoothly at the highest resolution, enhancing the user experience. Therefore, servers relying solely on static client characteristics for decision-making lack dynamism and fail to fully utilize client performance.

[0034] Based on this, embodiments of this application provide a service request decision-making method, apparatus, and device. When making a service request decision, the server makes a decision based on the client's fixed static characteristics, while the client makes a decision based on the client's real-time changing dynamic characteristics. This allows for full utilization of the client's performance and improves the flexibility of service request decision-making.

[0035] To facilitate understanding of the service request decision-making method provided in the embodiments of this application, the following is combined with... Figure 1 The example scenario is shown below. See also... Figure 1 As shown in the figure, this figure is a schematic diagram of an exemplary application scenario provided in the embodiments of this application.

[0036] This application embodiment can be applied to a server that makes service request decisions. When a client needs to request a service from the server, it triggers the sending of a service request to the server. The server can receive the service request sent by the client and determine the client's static characteristics through the service request. Then, it obtains the decision corresponding to the service request, which includes static decision conditions, a first dynamic decision condition, and the logical relationship between the decision conditions. The client's static characteristics are matched with the static decision conditions to simplify the decision and generate a simplified decision. If the simplified decision includes at least one second dynamic decision condition, the simplified decision is sent to the client so that the client can generate a decision result indicating whether or not the service request can be responded to based on the client's dynamic characteristics and the second dynamic decision condition. Alternatively, if the simplified decision is a decision result indicating whether or not the service request can be responded to, the decision result is directly sent to the client. Thus, the server makes service request decisions based on the client's fixed static characteristics, and the client makes service request decisions based on the client's real-time changing dynamic characteristics, thereby making full use of the client's performance and improving the flexibility of service request decision-making.

[0037] Those skilled in the art will understand that Figure 1 The schematic diagram shown is merely one example in which embodiments of this application can be implemented. The scope of application of the embodiments of this application is not limited by any aspect of this framework.

[0038] To facilitate understanding of this application, a service request decision-making method provided by an embodiment of this application will be described below with reference to the accompanying drawings.

[0039] See Figure 2 As shown, this figure is a flowchart of a service request decision-making method provided in an embodiment of this application. Figure 2 As shown, the method may include S201-S205:

[0040] S201: Receive service requests sent by clients and determine the static characteristics of clients through service requests.

[0041] When a client needs to request a service from a server, it sends a service request. For example, when a client needs to record video, it selects the desired resolution and initiates a video recording request, generating a service request which it then sends to the server. The service request typically carries basic client information, such as the client's device model, client version, and operating system type. It may also carry information related to the requested service, such as the service type and request parameters. Specifically, the service type could be recording or playback, and the request parameters could be the requested recording resolution or playback resolution.

[0042] After receiving a service request from a client, the server parses the request to obtain the client's static characteristics. These static characteristics can be understood as fixed and unchanging features of the client, such as device hardware information like CPU model and RAM capacity.

[0043] In one possible implementation, S201 receives a service request sent by the client, and determining the specific implementation of the client's static characteristics through the service request may include:

[0044] A1: Receive service requests sent by clients and obtain basic client information from the service requests.

[0045] When a server receives a service request from a client, it can retrieve the client's basic information carried in the request. However, to conserve communication overhead between the client and server, the client's basic information is typically limited. Therefore, the server needs to further determine the client's static characteristics based on this basic information.

[0046] A2: Based on the mapping relationship of the client's basic information, determine the client's static characteristics corresponding to the client's basic information.

[0047] In this embodiment, the server can pre-set mapping relationships between different client basic information and client static characteristics, such as the mapping relationship between device model and hardware information. Therefore, the server can obtain the client static characteristics corresponding to the client basic information based on the mapping relationship. That is, the server can obtain a relatively diverse range of client static characteristics through service requests.

[0048] S202: Obtain the decision corresponding to the service request. The decision includes the decision conditions and the logical relationship between the decision conditions. The decision conditions include static decision conditions and the first dynamic decision condition.

[0049] The server is pre-configured with decisions corresponding to different service requests. For example, it might decide whether a device with certain hardware information can record at the highest possible resolution. The decision result is typically a binary classification: yes or no.

[0050] Decision-making includes decision conditions and the logical relationships between them. The logical relationship between decision conditions generally refers to a relationship established through AND or OR logic. For example, if a decision includes decision conditions C1, C2, and C3, the decision is true if all three conditions are true; that is, the logical relationship between the decision conditions is established through AND logic. As another example, if a decision includes decision conditions C1, C2, and C3, the decision is true if any one of C1, C2, or C3 is true; that is, the logical relationship between the decision conditions is established through OR logic.

[0051] The decision conditions include static decision conditions and a first dynamic decision condition. Static decision conditions can be matched with static features of the client, and the server obtains the matching result of whether the client's static features match the corresponding static decision condition. Dynamic decision conditions can be matched with dynamic features of the client, and the client obtains the matching result of whether the client's dynamic features match the corresponding dynamic decision condition. In this embodiment, the dynamic decision condition included in the decision is the first dynamic decision condition.

[0052] S203: Based on the matching results between the client's static features and static decision conditions, as well as the logical relationship between the decision conditions, the decision is simplified to generate a simplified decision.

[0053] The server can match client static features with corresponding static decision conditions to obtain the matching results. Then, based on the logical relationships between the decision conditions, it simplifies the decision and generates a simplified decision. If the matching of client static features cannot directly determine whether the client can respond to the service request, it means that the client dynamic features need to be matched with dynamic decision conditions, and a simplified decision including at least one second dynamic decision condition is generated.

[0054] During the process of generating simplified decisions, the decisions may be pruned based on the matching results between client static features and static decision conditions, removing some decision conditions. In this case, the simplified decision may include one second dynamic decision, or multiple second dynamic decision conditions and the logical relationships between them. Each second dynamic decision condition is at least one of the first dynamic decision conditions. On one hand, since the server has already completed the matching between client static features and static decision conditions, the simplified decision no longer includes static decision conditions. On the other hand, based on the matching results between client static features and static decision conditions, and the logical relationships between decision conditions, it has been determined that some dynamic decision conditions cannot be met. These dynamic decision conditions are also removed from the decision, ensuring that the number of second dynamic decision conditions included in the simplified decision is less than or equal to the number of first dynamic decision conditions.

[0055] In this embodiment, S203 simplifies the decision based on the matching result of the client's static features and the static decision conditions, as well as the logical relationship between the decision conditions. The specific implementation process of generating the simplified decision can be found in the following embodiments, and will not be repeated here.

[0056] S204: If the simplified decision includes a second dynamic decision condition, the simplified decision is sent to the client so that the client generates a decision result indicating whether or not a service request can be responded to, based on the matching result between the client's dynamic characteristics and the second dynamic decision condition.

[0057] S205: If the simplified decision includes multiple second dynamic decision conditions and the logical relationship between the second dynamic decision conditions, the simplified decision is sent to the client so that the client generates a decision result indicating whether or not a service request can be responded to based on the matching result of the client's dynamic characteristics with the second dynamic decision conditions and the logical relationship between the second dynamic decision conditions.

[0058] A simplified decision is sent to the client. When the simplified decision includes a second dynamic decision condition, the client needs to obtain the current client dynamic characteristics corresponding to that second dynamic decision condition. Client dynamic characteristics can be understood as the client's real-time changing features, such as processor temperature, processor load, memory load, battery level, battery load, and behavioral markers. Further, the client matches these client dynamic characteristics with the corresponding second dynamic decision condition, and generates the final decision result based on the matching result.

[0059] Similarly, when simplified decision-making involves a second dynamic decision condition and the logical relationships between these conditions, the client needs to obtain the current client dynamic features corresponding to the second dynamic decision condition. The client matches these dynamic features with the corresponding second dynamic decision conditions and generates the final decision result based on the matching results and the logical relationships between the second dynamic decision conditions.

[0060] When the decision indicates that the client can respond to the service request, the client responds to the service request; when the decision indicates that the client cannot respond to the service request, the client cannot respond to the service request.

[0061] In one possible implementation, after S203, the following is also included: if the simplified decision is a decision result used to indicate whether a service request can be responded to, the decision result is sent to the client.

[0062] The server can match client static features with corresponding static decision conditions to obtain the matching results. Then, based on the logical relationships between the decision conditions, it simplifies the decision and generates a simplified decision. If simplifying the decision through matching client static features can directly determine whether the client can respond to the service request, then a simplified decision is generated. In this case, the generated simplified decision directly indicates whether the service request can be responded to.

[0063] The decision result is sent to the client. If the client receives the decision result, and the decision result indicates that the client can respond to the service request, then the client responds to the service request. If the decision result indicates that the client cannot respond to the service request, then the client cannot respond to the service request.

[0064] To facilitate understanding, the above embodiments will be further illustrated with examples.

[0065] The client sends a service request to the server to record video at the highest recording resolution. The server obtains the decision corresponding to this service request: if the device processor is H1 and the processor temperature is less than 40 degrees Celsius, video recording can be performed at the highest recording resolution; otherwise, video recording can only be performed at the default resolution. Here, device processor H1 is the static decision condition, and processor temperature less than 40 degrees Celsius is the first dynamic decision condition. The logical relationship between the decision conditions is a pass / fail AND condition.

[0066] The server obtains the client's static characteristic "device processor CPU" based on the service request. If the CPU is not H1, a simplified decision is directly generated, which is that video recording cannot be performed at the highest recording resolution. If the CPU is H1, a simplified decision is generated, which includes the second dynamic decision condition that the processor temperature is less than 40 degrees Celsius.

[0067] The decision result or simplified decision is sent to the client. When the client receives a simplified decision including the second dynamic decision condition, it obtains the client's dynamic feature "current processor temperature" and determines whether the current processor temperature is less than 40 degrees Celsius. If the processor temperature is less than 40 degrees Celsius, a decision result is generated that video recording can be performed at the highest recording resolution, and the client performs video recording at the highest recording resolution. If the processor temperature is not less than 40 degrees Celsius, a decision result is generated that video recording cannot be performed at the highest recording resolution, and the client can only perform video recording at the default recording resolution. When the client receives a simplified decision as the decision result, the client can only perform video recording at the default recording resolution.

[0068] In this way, by making service request decisions in collaboration between the server and the client, we can combine performance indicators at the device level with the device status at the current time to make combined decisions, making the decision-making more flexible.

[0069] Based on the descriptions in S201-S205, this embodiment of the application, upon receiving a service request from a client, first determines the client's static characteristics through the service request. Then, it obtains the decision corresponding to the service request, which includes static decision conditions, a first dynamic decision condition, and the logical relationships between these decision conditions. Based on the matching results between the client's static characteristics and the static decision conditions, and the logical relationships between the decision conditions, the decision is simplified to generate a simplified decision. If the simplified decision includes at least one second dynamic decision condition, the simplified decision is sent to the client, enabling the client to generate a decision result indicating whether or not it can respond to the service request based on its dynamic characteristics and the second dynamic decision condition. This approach integrates the client's fixed static characteristics and its real-time changing dynamic characteristics during the decision generation process, thereby fully utilizing the client's performance and improving the flexibility of service request decision-making.

[0070] See Figure 3 As shown, a flowchart for generating simplified decisions is illustrated. In one possible implementation, S203 simplifies the decision based on the matching results between the client's static features and static decision conditions, as well as the logical relationship between the decision conditions. The specific implementation of generating simplified decisions may include S301-S305:

[0071] S301: Match the client's static features with the corresponding static decision conditions to generate matching results.

[0072] After acquiring the client's static features, the static decision conditions corresponding to these features are identified from the decisions and matched to generate a matching result. For example, if the client's static feature is "device processor", then the static decision condition "device processor is H1" can be identified from the decisions and matched to generate a matching result of "whether the device processor is H1".

[0073] In one possible implementation, a matching model, such as a neural network model or a deep learning model, can be used to match client static features with static decision conditions. Therefore, the specific implementation of S301 matching client static features with corresponding static decision conditions and generating the matching results may include:

[0074] If the static decision condition corresponding to the client's static feature is the model's judgment decision condition, input the client's static feature into the matching model of the corresponding static decision condition, and obtain the matching result of whether the client's static feature matches the corresponding static decision condition.

[0075] When the static decision condition is the model's judgment condition, it means that matching the client's static features with this static decision condition requires using a pre-established matching model. The client's static features are input into the matching model corresponding to the static decision condition, and the model's output yields the matching result of whether the client's static features match the corresponding static decision condition. For example, if the client's static feature is "client account information," and the corresponding static decision condition is "the client account belongs to a premium account," then the client's static features can be input into the matching model of the corresponding static decision condition, and the model will obtain the matching result of "whether the client account belongs to a premium account."

[0076] S302: Based on the matching results and the logical relationship between the decision conditions, remove the corresponding decision conditions from the decision.

[0077] Based on the matching results, unreachable logical relationship branches in the decision can be directly removed. The decision after removal only contains the potentially reachable dynamic decision conditions and their logical relationships.

[0078] In one possible implementation, the specific implementation of S302, which removes the corresponding decision conditions in the decision based on the matching results and the logical relationship between the decision conditions, may include:

[0079] If the matching result makes the corresponding logical relationship unsatisfied, the logical relationship corresponding to the matching result is determined as an unreachable logical relationship, and the decision conditions associated with the unreachable logical relationship are removed from the decision.

[0080] If the matching result satisfies the corresponding logical relation, the logical relation corresponding to the matching result is determined as a reachable logical relation, and the static decision conditions associated with the reachable logical relation are removed from the decision.

[0081] In this embodiment, if the matching result of a certain static decision condition causes the corresponding logical relationship to be unsatisfied, then other decision conditions associated with that logical relationship do not need to be matched anymore, and all decision conditions associated with that logical relationship can be removed from the decision. For example, see... Figure 4 The diagram illustrates a simplified decision generation process. Assume C1 is the first dynamic decision condition, C2 is the static decision condition, and the logical relationship between C1 and C2 is AND. When the matching result of C2 is false, the logical relationship between C1 and C2 must also be false. In this case, the logical relationship is unreachable, and the decision conditions C1 and C2 associated with this logical relationship are removed from the decision.

[0082] If the matching result of a static decision condition satisfies the corresponding logical relation, then the static decision condition associated with that logical relation is removed from the decision, so that the decision after removal only contains dynamic decision conditions. For example, see below. Figure 4 As shown, when the matching result of C2 is true, the logical relationship between C1 and C2 may be true. At this time, the logical relationship is a reachable logical relationship. The static decision condition C2 associated with this logical relationship is removed from the decision. The decision after removal only includes C1. At this time, C1 is changed to the second dynamic decision condition C1.

[0083] For example, see Figure 5 The diagram illustrates another simplified decision generation process. Assume C1, C4, and C5 are the first dynamic decision conditions, and C2 and C3 are the static decision conditions. The logical relationship between C1 and C2 is AND, the logical relationship between C3 and C4 is AND, and the logical relationship between the two AND relationships and C5 is OR. When the matching result of C3 is false, the logical relationship corresponding to C3 is not satisfied; this logical relationship is an unreachable logical relationship, and the decision conditions C3 and C4 associated with this logical relationship are removed from the decision. When the matching result of C2 is true, the logical relationship corresponding to C2 may be satisfied; this logical relationship is a reachable logical relationship, and the static decision condition C2 associated with this logical relationship is removed from the decision. Since OR is also a reachable logical relationship, the first dynamic decision condition C5 can be retained. The decision after removal includes C1 and C5, and the logical relationship between C1 and C5 is OR. In this case, C1 and C5 are the second dynamic decision conditions.

[0084] S303: If, after removing the corresponding decision conditions in the decision, there are no remaining decision conditions in the decision, a simplified decision is obtained as the decision result.

[0085] If no decision conditions remain after the removal process, then the decision result can be obtained directly. For example, see... Figure 4 As shown, when both decision conditions C1 and C2 are removed from the decision, it means the decision is false, and the decision result can be obtained directly. In this case, a simplified decision is obtained.

[0086] S304: If, after removing the corresponding decision conditions in the decision, there is a remaining first dynamic decision condition in the decision, the remaining first dynamic decision condition in the decision is determined as the second dynamic decision condition, resulting in a simplified decision that includes a second dynamic decision condition.

[0087] S305: If, after removing the corresponding decision conditions in the decision, there are multiple remaining first dynamic decision conditions in the decision, the remaining first dynamic decision conditions in the decision are determined as second dynamic decision conditions, and the logical relationship between the second dynamic decision conditions is obtained, resulting in a simplified decision including multiple second dynamic decision conditions and the logical relationship between the second dynamic decision conditions.

[0088] If there is one remaining first dynamic decision condition in the simplified decision, this remaining first dynamic decision condition is determined as the second dynamic decision condition, resulting in a simplified decision including one second dynamic decision condition. If there are multiple remaining first dynamic decision conditions in the simplified decision, these remaining first dynamic decision conditions are determined as second dynamic decision conditions, and the logical relationships between the second dynamic decision conditions are obtained as the simplification logic. In this case, it means that the decision result cannot be directly obtained through matching static decision conditions; the client still needs to make further decisions based on the simplified decision including the second dynamic decision conditions.

[0089] In this embodiment, the decision can be pruned to obtain a simplified logic that contains only the second dynamic decision condition or only the second dynamic decision condition and its logical relationship, or a decision result that directly determines whether the decision is valid, thereby enabling the server and client to collaboratively complete the service request decision.

[0090] Furthermore, embodiments of this application can also conduct A / B experiments on the decision to obtain a better decision. In one possible implementation, the specific implementation of S202 obtaining the decision corresponding to the service request may include: obtaining either a first version decision or a second version decision corresponding to the service request.

[0091] Based on this, the service request decision-making method provided in this application embodiment may further include:

[0092] B1: After the client responds to the service request, obtain the response evaluation parameters of the first version decision or the second version decision.

[0093] B2: Based on the response evaluation parameters of the first or second version decision, determine the first or second version decision as the decision corresponding to the service request.

[0094] When setting decisions, it may sometimes be difficult to determine which version of the decision is better. For example, is it better to allow clients to record at the highest recording resolution when the processor temperature is below 40 degrees Celsius, or when the processor temperature is below 45 degrees Celsius? In such cases, multiple versions of the policy can be pre-set, and A / B experiments can be conducted on different versions of the decision to determine the better version. In practical applications, clients can be divided into different groups, and each group of clients can use a different version of the decision for service request decisions.

[0095] Specifically, for example, the decision can be divided into a first-version decision and a second-version decision, which can categorize clients into two groups. After receiving a service request from a client, the server determines the first-version or second-version decision corresponding to the service request based on the client's group, and then executes steps S203-S205 of this embodiment. After the client responds to the service request, the server can obtain the response evaluation parameters of the first-version or second-version decision from the client. These response evaluation parameters are relevant service response evaluation parameters when the client responds to the service request, such as response time and response effect parameters.

[0096] Based on the response evaluation parameters of the first or second version decision obtained from different clients, by comparing the response evaluation parameters of the first or second version decision, it can be determined which version of the decision is better, and the better decision is determined as the decision corresponding to the final service request.

[0097] In this embodiment of the application, A / B experiments can be conducted on different versions of the decision to obtain a better decision, thereby further improving the effectiveness of service request decision-making.

[0098] Furthermore, embodiments of this application may also perform a gray-scale rollout test on the decision before making a version update to determine whether to update the decision. In one possible implementation, the specific implementation of S202, obtaining the decision corresponding to the service request, may include: when the client is determined to be the target client through the service request, obtaining the update version decision corresponding to the service request.

[0099] Based on this, the service request decision-making method provided in this application embodiment may further include:

[0100] C1: After the client responds to the service request, obtain the response evaluation parameters for the update version decision;

[0101] C2: Based on the response evaluation parameters of the updated version decision, determine whether to confirm the updated version decision as the decision corresponding to the service request.

[0102] When a decision needs to be updated, a security guarantee is needed if the new version is widely adopted. Therefore, in this embodiment, a phased rollout can be implemented over a certain period to observe the changes. A subset of clients can be allowed to use the new version first. If no issues arise, the decision version can then be updated.

[0103] In practical applications, a subset of clients can be selected as target clients, for example, 10% of clients can be randomly selected. After receiving a service request from a client, if the client is a target client, the server obtains the updated version decision corresponding to the service request as the decision for the service request, and then executes steps S203-S205 of this embodiment. After the client responds to the service request, response evaluation parameters of the updated version decision can be obtained from the client. These response evaluation parameters are relevant service response evaluation parameters when the client responds to the service request, such as response time and response effect parameters. Based on the response evaluation parameters of the updated version decisions obtained from different target clients, it can be determined whether to determine the updated version decision as the final decision for the service request.

[0104] In this embodiment of the application, a gray-scale scaling experiment can also be conducted on the decision of the updated version to ensure the security of the decision when the version is updated.

[0105] Based on the service request decision-making method provided in the above-described method embodiments, this application also provides a service request decision-making device, which will be described below with reference to the accompanying drawings.

[0106] See Figure 6 As shown in the figure, this is a schematic diagram of the structure of a service request decision device provided in an embodiment of this application. Figure 6 As shown, the service request decision-making device includes:

[0107] The determining unit 601 is used to receive a service request sent by the client and determine the client's static characteristics through the service request;

[0108] The first acquisition unit 602 is used to acquire the decision corresponding to the service request, the decision including decision conditions and the logical relationship between the decision conditions; the decision conditions include static decision conditions and a first dynamic decision condition.

[0109] The generation unit 603 is used to simplify the decision based on the matching result between the client static features and the static decision conditions, as well as the logical relationship between the decision conditions, and generate a simplified decision.

[0110] The first sending unit 604 is configured to send the simplified decision to the client if the simplified decision includes a second dynamic decision condition, so that the client generates a decision result indicating whether the service request can be responded to based on the matching result between the client's dynamic characteristics and the second dynamic decision condition.

[0111] The second sending unit 605 is configured to send the simplified decision to the client if the simplified decision includes multiple second dynamic decision conditions and the logical relationship between the second dynamic decision conditions, so that the client generates a decision result indicating whether the service request can be responded to based on the matching result of the client's dynamic characteristics and the second dynamic decision conditions, and the logical relationship between the second dynamic decision conditions.

[0112] The second dynamic decision condition is at least one of the first dynamic decision conditions.

[0113] In one possible implementation, the device further includes:

[0114] The third sending unit is configured to send the decision result to the client if the simplified decision is a decision result indicating whether the service request can be responded to.

[0115] In one possible implementation, the generating unit includes:

[0116] The matching subunit is used to match the client's static features with the corresponding static decision conditions to generate a matching result;

[0117] The removal subunit is used to remove the corresponding decision conditions in the decision according to the matching result and the logical relationship between the decision conditions;

[0118] The first determining subunit is used to obtain a simplified decision as the decision result if, after removing the corresponding decision conditions in the decision, there are no remaining decision conditions in the decision.

[0119] The second determining subunit is used to determine the remaining first dynamic decision condition in the decision as the second dynamic decision condition if there is a remaining first dynamic decision condition in the decision after removing the corresponding decision conditions in the decision, thereby obtaining a simplified decision including a second dynamic decision condition.

[0120] The third determining subunit is used to determine the remaining first dynamic decision conditions as second dynamic decision conditions if multiple first dynamic decision conditions remain after removing the corresponding decision conditions in the decision, and to obtain the logical relationship between the second dynamic decision conditions to obtain a simplified decision including multiple second dynamic decision conditions and the logical relationship between the second dynamic decision conditions.

[0121] In one possible implementation, the removal subunit is specifically used for:

[0122] If the matching result causes the corresponding logical relationship to be unsatisfied, the logical relationship corresponding to the matching result is determined as an unreachable logical relationship, and the decision conditions associated with the unreachable logical relationship are removed from the decision.

[0123] If the matching result satisfies the corresponding logical relationship, the logical relationship corresponding to the matching result is determined as a reachable logical relationship, and the static decision conditions associated with the reachable logical relationship are removed from the decision.

[0124] In one possible implementation, the matching subunit is specifically used for:

[0125] If the static decision condition corresponding to the client static feature is a model judgment decision condition, the client static feature is input into the matching model of the corresponding static decision condition to obtain the matching result of whether the client static feature matches the corresponding static decision condition.

[0126] In one possible implementation, the determining unit includes:

[0127] The receiving and sending subunit is used to receive service requests sent by the client and obtain basic client information from the service requests;

[0128] The fourth determining subunit is used to determine the client static features corresponding to the client basic information based on the mapping relationship of the client basic information.

[0129] In one possible implementation, the first acquisition unit is specifically used for:

[0130] Obtain the first version decision or the second version decision corresponding to the service request;

[0131] The device further includes:

[0132] The second acquisition unit is used to acquire the response evaluation parameters of the first version decision or the second version decision after the client responds to the service request;

[0133] The determining unit is configured to determine the first version decision or the second version decision as the decision corresponding to the service request based on the response evaluation parameters of the first version decision or the second version decision.

[0134] In one possible implementation, the first acquisition unit is specifically used for:

[0135] When the client is determined to be the target client through the service request, the update version decision corresponding to the service request is obtained;

[0136] The device further includes:

[0137] The third acquisition unit is used to acquire the response evaluation parameters of the update version decision after the client responds to the service request;

[0138] The judgment unit is used to determine, based on the response evaluation parameters of the updated version decision, whether to identify the updated version decision as the decision corresponding to the service request.

[0139] Based on the service request decision-making method provided in the above-described method embodiments, this application also provides an electronic device, including: one or more processors; a storage device storing one or more programs thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the service request decision-making method described in any of the above embodiments.

[0140] The following is for reference. Figure 7 The diagram illustrates a structural schematic of an electronic device 1300 suitable for implementing embodiments of this application. The terminal devices in these embodiments may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Android Devices), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs (televisions), desktop computers, etc. Figure 7 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0141] like Figure 7As shown, electronic device 1300 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 1301, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1302 or a program loaded from storage device 1306 into random access memory (RAM) 1303. RAM 1303 also stores various programs and data required for the operation of electronic device 1300. Processing device 1301, ROM 1302, and RAM 1303 are interconnected via bus 1304. Input / output (I / O) interface 1305 is also connected to bus 1304.

[0142] Typically, the following devices can be connected to I / O interface 1305: input devices 1306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1306 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1309. Communication device 1309 allows electronic device 1300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 1300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0143] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1309, or installed from storage device 1306, or installed from ROM 1302. When the computer program is executed by processing device 1301, it performs the functions defined in the methods of embodiments of this application.

[0144] The electronic device provided in this application embodiment belongs to the same inventive concept as the service request decision method provided in the above embodiment. Technical details not described in detail in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0145] Based on the service request decision-making method provided in the above-described embodiments, this application provides a computer-readable medium storing a computer program thereon, wherein the program, when executed by a processor, implements the service request decision-making method as described in any of the above embodiments.

[0146] It should be noted that the computer-readable medium described in the embodiments of this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the embodiments of this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the embodiments of this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0147] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0148] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0149] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned service request decision method.

[0150] Computer program code for performing the operations of the embodiments of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0151] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0152] The units described in the embodiments of this application can be implemented in software or hardware. The names of the units / modules do not necessarily limit the specific unit itself.

[0153] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0154] In the context of embodiments of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0155] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0156] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0157] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0158] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0159] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A service request decision-making method, characterized in that, The method includes: Receive service requests sent by clients and determine client static characteristics based on the service requests; Obtain the decision corresponding to the service request, the decision including decision conditions and the logical relationship between the decision conditions; the decision conditions include static decision conditions and a first dynamic decision condition; Based on the matching results between the client's static features and the static decision conditions, as well as the logical relationship between the decision conditions, the decision is simplified to generate a simplified decision. If the simplified decision includes a second dynamic decision condition, the simplified decision is sent to the client so that the client generates a decision result indicating whether the service request can be responded to based on the matching result between the client's dynamic characteristics and the second dynamic decision condition. If the simplified decision includes multiple second dynamic decision conditions and the logical relationship between the second dynamic decision conditions, the simplified decision is sent to the client so that the client generates a decision result indicating whether the service request can be responded to based on the matching result of the client's dynamic characteristics with the second dynamic decision conditions and the logical relationship between the second dynamic decision conditions. The second dynamic decision condition is at least one of the first dynamic decision conditions.

2. The method according to claim 1, characterized in that, The method further includes: If the simplified decision is a decision result indicating whether the service request can be responded to, the decision result is sent to the client.

3. The method according to claim 1, characterized in that, The step of simplifying the decision based on the matching results between the client's static features and the static decision conditions, and the logical relationship between the decision conditions, to generate a simplified decision includes: The client's static features are matched with the corresponding static decision conditions to generate matching results; Based on the matching results and the logical relationship between the decision conditions, the corresponding decision conditions in the decision are removed; If, after removing the corresponding decision conditions from the decision, no decision conditions remain in the decision, a simplified decision is obtained as the decision result. If, after removing the corresponding decision conditions in the decision, there is a remaining first dynamic decision condition in the decision, the remaining first dynamic decision condition in the decision is determined as the second dynamic decision condition, and a simplified decision including a second dynamic decision condition is obtained. If, after removing the corresponding decision conditions in the decision, there are multiple remaining first dynamic decision conditions in the decision, the remaining first dynamic decision conditions in the decision are determined as second dynamic decision conditions, and the logical relationship between the second dynamic decision conditions is obtained, resulting in a simplified decision including multiple second dynamic decision conditions and the logical relationship between the second dynamic decision conditions.

4. The method according to claim 3, characterized in that, The step of removing corresponding decision conditions from the decision based on the matching results and the logical relationship between the decision conditions includes: If the matching result causes the corresponding logical relationship to be unsatisfied, the logical relationship corresponding to the matching result is determined as an unreachable logical relationship, and the decision conditions associated with the unreachable logical relationship are removed from the decision. If the matching result satisfies the corresponding logical relationship, the logical relationship corresponding to the matching result is determined as a reachable logical relationship, and the static decision conditions associated with the reachable logical relationship are removed from the decision.

5. The method according to claim 3, characterized in that, The step of matching the client's static features with the corresponding static decision conditions to generate a matching result includes: If the static decision condition corresponding to the client static feature is a model judgment decision condition, the client static feature is input into the matching model of the corresponding static decision condition to obtain the matching result of whether the client static feature matches the corresponding static decision condition.

6. The method according to claim 1, characterized in that, The process of receiving a service request from a client and determining the client's static characteristics through the service request includes: Receive service requests sent by clients and obtain basic client information from the service requests; Based on the mapping relationship of the client's basic information, the client's static features corresponding to the client's basic information are determined.

7. The method according to any one of claims 1-6, characterized in that, The decision to obtain the service request includes: Obtain the first version decision or the second version decision corresponding to the service request; The method further includes: After the client responds to the service request, the response evaluation parameters of the first version decision or the second version decision are obtained; Based on the response evaluation parameters of the first version decision or the second version decision, the first version decision or the second version decision is determined as the decision corresponding to the service request.

8. The method according to any one of claims 1-6, characterized in that, The decision to obtain the service request includes: When the client is determined to be the target client through the service request, the update version decision corresponding to the service request is obtained; The method further includes: After the client responds to the service request, the response evaluation parameters of the update version decision are obtained; Based on the response evaluation parameters of the updated version decision, determine whether to identify the updated version decision as the decision corresponding to the service request.

9. A service request decision-making device, characterized in that, The device comprises: A determining unit is used to receive a service request sent by a client and determine the client's static characteristics through the service request. The first acquisition unit is used to acquire the decision corresponding to the service request, the decision including decision conditions and the logical relationship between the decision conditions; the decision conditions include static decision conditions and a first dynamic decision condition. The generation unit is used to simplify the decision based on the matching result between the client's static features and the static decision conditions, as well as the logical relationship between the decision conditions, and generate a simplified decision. The first sending unit is configured to send the simplified decision to the client if the simplified decision includes a second dynamic decision condition, so that the client generates a decision result indicating whether the service request can be responded to based on the matching result between the client's dynamic characteristics and the second dynamic decision condition. The second sending unit is configured to send the simplified decision to the client if the simplified decision includes multiple second dynamic decision conditions and the logical relationship between the second dynamic decision conditions, so that the client generates a decision result indicating whether the service request can be responded to based on the matching result of the client's dynamic characteristics and the second dynamic decision conditions, and the logical relationship between the second dynamic decision conditions. The second dynamic decision condition is at least one of the first dynamic decision conditions.

10. A service request decision-making device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the service request decision method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a terminal device, cause the terminal device to perform the service request decision method as described in any one of claims 1-8.

Images