Negative feedback content determination method and apparatus, electronic device, and storage medium

Abstract

Embodiments of the present application disclose a kind of negative feedback content determination method, device, electronic equipment and storage medium.The method comprises: obtaining the negative feedback content query request of target user;Wherein, the negative feedback content query request is generated based on recommendation instruction trigger or generated based on application start instruction trigger, and the user identifier of the target user is included in the negative feedback content query request;System parameters of each negative feedback service instance current time are acquired, and the weight iteration coefficient of each negative feedback service instance current time is determined based on each system parameter;According to the weight iteration coefficient of each negative feedback service instance, the instance weight of each negative feedback service instance current time is determined;According to each instance weight, the target negative feedback service instance is determined.Through the technical scheme disclosed in the embodiments of the present application, the load of system is reduced, and the efficiency of negative feedback content determination is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of intelligent recommendation technology, and in particular to a method, apparatus, electronic device, and storage medium for determining negative feedback content. Background Technology

[0002] Negative feedback enables recommendation systems to obtain genuine negative feedback from users, allowing them to de-weight or filter such content, reducing recommendations of irrelevant information and optimizing the user experience. Typical negative feedback systems rely on high-performance storage systems (such as Redis / Memcached). The process is roughly as follows: after a user provides negative feedback, the system stores it in real-time; upon the next request, the system retrieves the feedback from storage, and the recommendation system then performs subsequent actions (de-weighting or filtering). However, a large number of invalid requests can cause the storage system to become a performance bottleneck. During peak traffic periods, the storage system may crash due to excessive load, rendering the recommendation function unavailable and causing online outages. Summary of the Invention

[0003] This invention provides a method, apparatus, electronic device, and storage medium for determining negative feedback content, so as to reduce the system load and improve the efficiency of determining negative feedback content.

[0004] In a first aspect, embodiments of the present invention provide a method for determining negative feedback content, the method comprising:

[0005] Obtain a negative feedback content query request for the target user; wherein, the negative feedback content query request is generated based on a recommendation instruction or an application launch instruction, and the negative feedback content query request includes the user identifier of the target user;

[0006] Obtain the system parameters of each negative feedback service instance at the current moment, and determine the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters;

[0007] The instance weight of each negative feedback service instance at the current moment is determined based on the weight iteration coefficient of each negative feedback service instance.

[0008] The target negative feedback service instance is determined based on the weights of each instance, wherein the target negative feedback service instance is used to respond to the negative feedback content query request of the target user, obtain the query information of the negative feedback content, and output the query information of the negative feedback content.

[0009] The method by which the target negative feedback service instance responds to the target user's negative feedback content query request includes:

[0010] Based on the user identifier, determine whether the target user is a negative feedback user;

[0011] If the target user is a negative feedback user, then the negative feedback content of the target user is determined based on the user identifier.

[0012] Optionally, before retrieving the negative feedback content query request for the target user, the process may also include:

[0013] Establish a negative feedback content database and a negative feedback user database;

[0014] When a negative feedback action of any user is detected, obtain the negative feedback content and the negative feedback user corresponding to the negative feedback action.

[0015] The negative feedback content database and the negative feedback user database are updated based on the negative feedback content and the negative feedback user, respectively.

[0016] Optionally, after updating the negative feedback content database and the negative feedback user database based on the negative feedback content and the negative feedback user respectively, the method further includes:

[0017] The negative feedback user database is broadcast to all negative feedback service instances using Redis broadcast, and the negative feedback user set cache in each negative feedback service instance is updated.

[0018] Optionally, determining whether the target user is a negative feedback user based on the user identifier includes:

[0019] The user identifier is matched with each negative feedback user identifier in the negative feedback user database;

[0020] If a match is successful, the target user is determined to be a negative feedback user.

[0021] Optionally, the system parameters for the negative feedback service instance include CPU load rate, memory usage, and service response time;

[0022] Accordingly, the expression for determining the weight iteration coefficients of each negative feedback service instance at the current moment based on the system parameters includes:

[0023]

[0024] in, represents the weight iteration coefficient, cpuLoadRate represents the CPU load rate, memoryUsage represents the memory usage rate, and rt represents the service response time.

[0025] Optionally, determining the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient of each negative feedback service instance includes:

[0026] Obtain the weight of the negative feedback service instance at the previous moment, update the weight of the previous moment based on the instance weight of the negative feedback service instance at the current moment, and obtain the instance weight of the negative feedback service instance at the current moment.

[0027] Optionally, determining the target negative feedback service instance based on the weights of each instance includes:

[0028] The negative feedback service instance corresponding to the largest instance weight is determined as the target negative feedback service instance; or...

[0029] Based on the weights of each instance, the access probability of each negative feedback service instance is determined, and the negative feedback service instance with the highest access probability is determined as the target negative feedback service instance.

[0030] Optionally, after determining the negative feedback content of the target user based on the user identifier, the method further includes:

[0031] Based on the negative feedback content and the user identifier, the recommended content for the target user is determined, and the recommendation request for the target user is responded to.

[0032] Secondly, embodiments of the present invention also provide a negative feedback content determination device, the device comprising:

[0033] The negative feedback content query request acquisition module is used to acquire negative feedback content query requests for target users; wherein, the negative feedback content query request is generated based on a recommendation instruction or an application launch instruction, and the negative feedback content query request includes the user identifier of the target user;

[0034] The weight iteration coefficient determination module is used to obtain the system parameters of each negative feedback service instance at the current time, and determine the weight iteration coefficient of each negative feedback service instance at the current time based on the system parameters.

[0035] The instance weight determination module is used to determine the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient of each negative feedback service instance;

[0036] The target negative feedback instance determination module is used to determine the target negative feedback service instance according to the weight of each instance, wherein the target negative feedback service instance is used to respond to the negative feedback content query request of the target user, obtain the query information of the negative feedback content, and output the query information of the negative feedback content;

[0037] The target negative feedback instance determination module includes:

[0038] The negative feedback user determination submodule is used to determine whether the target user is a negative feedback user based on the user identifier;

[0039] The negative feedback content determination submodule is used to determine the negative feedback content of the target user based on the user identifier if the target user is a negative feedback user.

[0040] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0041] One or more processors;

[0042] Storage device for storing one or more programs.

[0043] When the one or more programs are executed by the one or more processors, the one or more processors implement the negative feedback content determination method provided in any embodiment of the present invention.

[0044] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the negative feedback content determination method provided in any embodiment of the present invention.

[0045] The technical solution of this invention specifically includes: acquiring a negative feedback content query request for a target user triggered by a recommendation instruction or an application launch instruction; obtaining negative feedback content query information for the target object based on the query request; acquiring system parameters of each negative feedback service instance at the current moment, determining the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters, and determining the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient; determining the negative feedback content query information for responding to the target user's negative feedback content query request based on the instance weights, obtaining the query information of the negative feedback content, and outputting the query information of the negative feedback content. A target negative feedback service instance is used to improve the efficiency of negative feedback content determination by identifying the highest-performing target negative feedback service instance among various negative feedback service instances. The method by which the target negative feedback service instance responds to the negative feedback content query request of the target user includes: determining whether the target user is a negative feedback user based on the user identifier; if the target user is a negative feedback user, then determining the target user's negative feedback content based on the user identifier. This achieves the interception of most invalid requests by the storage system, ensuring that only users with genuine negative feedback content query the negative feedback storage system, thus greatly reducing the load on the storage system and solving the performance bottleneck problem. The technical solution of this embodiment improves query efficiency by determining the target negative feedback service instance for the target user's negative feedback content query request, and during the response process, queries are performed on the target user based on the negative feedback user database to identify them as a negative feedback user, intercepting a large number of invalid requests and reducing the system's operational pressure. Simultaneously, querying the target user's negative feedback content based on the target user identifier improves the accuracy of the query. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of exemplary embodiments of the present invention, the accompanying drawings used in describing the embodiments are briefly introduced below. Obviously, the accompanying drawings described are only a portion of the drawings of the embodiments to be described in this invention, and not all of the drawings. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort.

[0047] Figure 1 This is a flowchart illustrating the method for determining negative feedback content provided in Embodiment 1 of the present invention;

[0048] Figure 2 This is a flowchart illustrating the method for determining negative feedback content provided in Embodiment 2 of the present invention;

[0049] Figure 3 This is a schematic diagram of the negative feedback content determination device provided in Embodiment 3 of the present invention;

[0050] Figure 4 This is a schematic diagram of the structure of the electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0051] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0052] Example 1

[0053] Figure 1 This is a flowchart of a method for determining negative feedback content according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the negative feedback content of a target user is determined based on a query request from that user; specifically, it is more applicable to situations where the target negative feedback service instance is determined based on the current system parameters of each feedback service instance to respond to the negative feedback content query request of the target user, obtain query information of the negative feedback content, and output the query information of the negative feedback content. This method can be executed by a negative feedback content determination device, which can be implemented in software and / or hardware.

[0054] Before introducing the technical solutions of the embodiments of the present invention, an exemplary application scenario of the embodiments of the present invention will be introduced first: When recommending content to a user based on the user's recommendations, the negative feedback content of the user is generally obtained, and the recommended content is determined and recommended based on the negative feedback content. The negative feedback content is based on the content generated when the user performs a negative feedback operation in advance. Currently, the method for determining negative feedback content generally involves storing the negative feedback content corresponding to any user's negative feedback operation in real time to a high-performance storage system; when the user makes the next request, the negative feedback content is retrieved from the storage system, and the recommendation system then performs corresponding subsequent operations based on the negative feedback content, such as downgrading or filtering the content, thereby recommending content that the user is interested in.

[0055] The aforementioned technical solution matches all users making recommendation requests to see if they have stored negative feedback content. However, since only a small percentage (around 1%) of users have performed negative feedback operations and stored negative feedback content, a large number of users without negative feedback also need to retrieve their negative feedback content from the storage system, resulting in a large number (99%) of meaningless requests. Furthermore, while the performance may be sufficient for a small platform (tens or even hundreds of millions of users), when the platform scales rapidly (reaching tens or even hundreds of millions of users) or experiences sudden traffic surges (such as the arrival of major livestreamers), every user request will query the storage system for negative feedback content, regardless of whether the user has it or not. In this situation, the storage system becomes the performance bottleneck of the recommendation system. During peak traffic periods, the storage system is likely to crash due to excessive load, rendering the recommendation function unavailable and causing online failures.

[0056] Therefore, to address the aforementioned technical problems, the technical solution of this invention proposes: obtaining a negative feedback content query request for a target user triggered by a recommendation instruction or an application launch instruction, and obtaining negative feedback content query information for the target object based on the query request; obtaining the system parameters of each negative feedback service instance at the current moment, and determining the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters, and determining the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient of each negative feedback service instance; determining the negative feedback content query request for responding to the target user based on the instance weights, obtaining the query information of the negative feedback content, and outputting the negative feedback. The content query information targets a negative feedback service instance. By identifying the best-performing target negative feedback service instance among various negative feedback service instances, the efficiency of determining negative feedback content is improved. The method by which the target negative feedback service instance responds to the negative feedback content query request of the target user includes: determining whether the target user is a negative feedback user based on the user identifier; if the target user is a negative feedback user, then determining the target user's negative feedback content based on the user identifier. This achieves the goal of intercepting most invalid requests for the storage system. Only users with genuine negative feedback content will query the negative feedback storage system for negative feedback content, which greatly reduces the load on the storage system and thus solves the performance bottleneck problem.

[0057] like Figure 1 As shown, the technical solution specifically includes the following steps:

[0058] S110, Obtain a query request for negative feedback content to the target user.

[0059] In this embodiment of the invention, the target user can be the user who submitted the recommendation request. The negative feedback content query request can be a request to check whether the target user has stored negative feedback content. The negative feedback content query request includes the target user's user identifier, so that the target user's negative feedback content can be queried based on that user identifier.

[0060] Optionally, the method for obtaining a negative feedback content query request for the target user can be based on a recommendation instruction trigger. The recommendation instruction can be a recommendation instruction received by the target user when sending a content recommendation request. Specifically, a negative feedback content query request for the target user is triggered when a recommendation instruction from the target user is detected.

[0061] Optionally, the method for obtaining a query request for negative feedback content to the target user can also be based on generation triggered by an application startup command. The application startup command can be a command sent when the application starts. Specifically, a query request for negative feedback content to the target user is triggered when the application startup command is detected.

[0062] S120. Obtain the system parameters of each negative feedback service instance at the current moment, and determine the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters.

[0063] It is understood that a negative feedback service instance is a server or processor used to execute the current negative feedback content determination method. In this embodiment of the invention, the current recommendation system includes at least one negative feedback service instance. The system parameters of the negative feedback service instance at the current moment are parameters used to determine the weight iteration coefficient of the negative feedback service instance at the current moment. Specifically, the system parameters of the negative feedback service instance include CPU load rate, memory utilization rate, and service response time. The weight iteration coefficient of the negative feedback service instance at the current moment is a parameter coefficient used to determine the instance weight of the negative feedback service instance at the current moment.

[0064] To clearly illustrate the method for determining the weight iteration coefficients of each negative feedback service instance, this embodiment takes determining the weight iteration coefficient of any negative feedback service instance as an example: Based on a preset time interval, the system parameters of the negative feedback service instance are obtained. For example, the preset time interval can be 1 minute or 1.5 minutes; this embodiment does not impose any restrictions on this. Optionally, the expression for determining the weight iteration coefficients of the negative feedback service instance at the current moment based on the system parameters of the negative feedback service instance at the current moment can be:

[0065]

[0066] in, represents the weight iteration coefficient, cpuLoadRate represents the CPU load rate, memoryUsage represents the memory usage rate, and rt represents the service response time.

[0067] In this embodiment of the invention, the reason for using the above three calculation items as the expression for calculating the weight iteration coefficient is that the load balancing weight of the current negative feedback service instance is obtained after calculating the CPU load rate, memory utilization rate and service response time in a preset form, and the three preprocessed system parameters are multiplied together; in this embodiment of the invention, calculating the above at least three system parameters makes the parameter information for calculating the weight iteration coefficient more comprehensive and the calculation result more accurate.

[0068] Specifically, the first term of the expression is: This expression determines the CPU idle rate of the current negative feedback service instance by subtracting from the CPU load rate, and then performs a division calculation less than 1 to make the CPU idle rate result clearer. Specifically, the current expression indicates that when the CPU load rate cpuLoadRate is greater than 50%, the load balancing weight of the negative feedback service instance at the current moment will decrease, and when cpuLoadRate is less than 50%, the load balancing weight of the negative feedback service instance at the current moment will increase. It further considers how to determine the target service instance in each negative feedback service instance from the perspective of CPU load.

[0069] The second term of the expression is: This expression is based on subtracting memory usage to determine the memory idle rate of the current negative feedback service instance, and then performing a division of less than 1 to make the memory idle rate result clearer. Specifically, the current expression indicates that when memory usage is greater than 50%, the load balancing weight of the negative feedback service instance will decrease, and when memory usage is less than 50%, the load balancing weight of the negative feedback service instance will increase. It further considers how to determine the target service instance among each negative feedback service instance from a memory perspective.

[0070] The third term of the expression is: This expression determines the load weight of the current negative feedback service instance's service response by identifying its proportion within the total service response time of all negative feedback service instances. It then uses subtraction to determine the proportion of other negative feedback service instances' service response times within the total service response time of all negative feedback service instances. Specifically, the expression indicates that the larger the service response time *rt*, the larger the proportion of the current negative feedback service instance's service response time within the total service response time of all negative feedback service instances. This means that the proportion of other negative feedback service instances' responses within the total service response time of all negative feedback service instances decreases, thus causing the current load balancing weight of the current negative feedback service instance to decay more rapidly. Furthermore, it considers how to determine the target service instance among all negative feedback service instances from the perspective of service response time.

[0071] After processing CPU load rate, memory utilization rate, and service response time, the results are multiplied to obtain the final weight iteration coefficient, which is used to determine the load balancing weight of the current negative feedback service instance. This allows for faster determination of the target negative feedback service instance for each instance. Compared to existing technologies that directly use system parameters for weighting or multiplication to determine system performance, this embodiment of the invention uses preprocessing of system parameters followed by multiplication to determine the weight iteration coefficient, and then uses the iteration coefficient and the current moment to determine the system weight performance, which is more accurate.

[0072] S130. Determine the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient of each negative feedback service instance.

[0073] It is understandable that instance weight is the proportion of weight that the current negative feedback instance accounts for among all negative feedback service instances in the current recommendation system.

[0074] Optionally, the method for determining the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient of each negative feedback service instance may be: obtaining the weight of the negative feedback service instance at the previous moment, updating the weight of the previous moment based on the instance weight of the negative feedback service instance at the current moment, and obtaining the instance weight of the negative feedback service instance at the current moment.

[0075] Specifically, taking the determination of the instance weight of any negative feedback service instance as an example: Suppose we need to determine the current time t of the negative feedback service instance. j The instance weight is obtained by retrieving the instance weight w of the negative feedback service instance at the previous time step. i (t j-1 ), and the weight iteration coefficient α of the negative feedback service instance at the current moment as determined in the above embodiments. i (t jIf the instance weight is obtained by multiplying the instance weight from the previous time step with the weight iteration coefficient from the current time step, then the instance weight w of the negative feedback service instance at the current time step is obtained. i (t j ).

[0076] In some embodiments, when each negative feedback service instance is started, the weights of each instance are the same, and w(t0) is 1.0 for all instances. At this time, any instance can be selected as the target negative feedback service instance.

[0077] S140. Determine the target negative feedback service instance based on the weights of each instance.

[0078] S150. Send the negative feedback content query request to the target negative feedback service instance, and obtain the negative feedback content determined by the target negative feedback service instance based on the user identifier.

[0079] In this embodiment of the invention, the target negative feedback instance is used by the target negative feedback service instance to respond to the target user's negative feedback content query request, obtain the query information of the negative feedback content, and output the query information of the negative feedback content. Based on the technical solution of the above embodiment, the instance weight of each negative feedback instance in the current recommendation system is determined, and the target negative feedback service instance is determined based on the instance weight of each instance.

[0080] Optionally, the method for determining the target negative feedback service instance based on the weights of each instance can be: the negative feedback service instance corresponding to the instance with the highest weight is determined as the target negative feedback service instance. Specifically, the weights of each instance are sorted from largest to smallest, and the negative feedback service instance with the highest weight is determined as the target negative feedback service instance.

[0081] Optionally, the method for determining the target negative feedback service instance based on the weight of each instance can also be: determining the access probability of each negative feedback service instance based on the weight of each instance, and determining the negative feedback service instance with the highest access probability as the target negative feedback service instance.

[0082] Specifically, the access probability of each negative feedback service instance is determined based on the following expression, and based on each access probability value, the negative feedback service instance with the highest access probability value is selected as the target negative feedback service instance. The expression for determining the access probability is as follows:

[0083]

[0084] In this embodiment of the invention, the method for a target negative feedback service instance to respond to a target user's negative feedback content query request includes: determining whether the target user is a negative feedback user based on a user identifier; if the target user is a negative feedback user, then determining the target user's negative feedback content based on the user identifier.

[0085] Specifically, the method for determining whether a target user is a negative feedback user based on the user identifier can be as follows: match the user identifier with each negative feedback user identifier in the negative feedback user database; if the match is successful, the target user is determined to be a negative feedback user, and a negative feedback content query request corresponding to the negative feedback user is executed to obtain the negative feedback query result; if the match fails, the target user is determined to be a non-negative feedback user, the negative feedback query result is empty, and there is no need to execute the negative feedback content query request, thus reducing the load pressure caused by invalid requests.

[0086] The technical solution of this invention specifically includes: acquiring a negative feedback content query request for a target user triggered by a recommendation instruction or an application launch instruction; obtaining negative feedback content query information for the target object based on the query request; acquiring system parameters of each negative feedback service instance at the current moment, determining the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters, and determining the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient; determining the negative feedback content query information for responding to the target user's negative feedback content query request based on the instance weights, obtaining the query information of the negative feedback content, and outputting the query information of the negative feedback content. A target negative feedback service instance is used to improve the efficiency of negative feedback content determination by identifying the highest-performing target negative feedback service instance among various negative feedback service instances. The method by which the target negative feedback service instance responds to the negative feedback content query request of the target user includes: determining whether the target user is a negative feedback user based on the user identifier; if the target user is a negative feedback user, then determining the target user's negative feedback content based on the user identifier. This achieves the interception of most invalid requests by the storage system, ensuring that only users with genuine negative feedback content query the negative feedback storage system, thus greatly reducing the load on the storage system and solving the performance bottleneck problem. The technical solution of this embodiment improves query efficiency by determining the target negative feedback service instance for the target user's negative feedback content query request, and during the response process, queries are performed on the target user based on the negative feedback user database to identify them as a negative feedback user, intercepting a large number of invalid requests and reducing the system's operational pressure. Simultaneously, querying the target user's negative feedback content based on the target user identifier improves the accuracy of the query.

[0087] Example 2

[0088] Figure 2 This is a flowchart of a method for determining negative feedback content according to Embodiment 2 of the present invention. Based on the above embodiments, this embodiment adds the step of "obtaining a negative feedback content database and a negative feedback user database." Explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here. See also... Figure 2The method for determining negative feedback content provided in this embodiment includes:

[0089] S210, Obtain the negative feedback content database and the negative feedback user database.

[0090] In this embodiment of the invention, the feedback content database can be a database used to store negative feedback content generated by negative feedback users when they perform negative feedback operations. The feedback user database can be a database used to store negative feedback users who perform negative feedback operations. Here, a negative feedback operation can be an operation where a user marks content they are not interested in.

[0091] Specifically, a negative feedback content database and a negative feedback user database are established, and negative feedback operations of each user are detected. When a negative feedback operation of any user is detected, the negative feedback content and the corresponding negative feedback user are obtained; the negative feedback content database and the negative feedback user database are updated based on the negative feedback content and the negative feedback user, respectively.

[0092] In the above embodiments, since the method of responding to the target user's negative feedback content query request is performed by the target negative feedback service instance, the update of the negative feedback content database and the negative feedback user database is also performed within the target negative feedback service instance, which may cause inconsistency in the cache of multiple instances. To solve this problem, the present invention proposes a Redis broadcast method to broadcast the negative feedback user database to all negative feedback service instances, updating the negative feedback user database and negative feedback content database in each negative feedback service instance. This ensures that while updating the negative feedback user database and negative feedback content database of a certain negative feedback service instance, a broadcast is simultaneously sent to all other negative feedback service instances. When other instances receive this update, they also update the negative feedback user database and negative feedback content database in their memory, thereby resolving the problem of inconsistency in the memory cache of all negative feedback service instances.

[0093] S220, Obtain a query request for negative feedback content to the target user.

[0094] S230. Obtain the system parameters of each negative feedback service instance at the current moment, and determine the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters.

[0095] S240. Determine the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient of each negative feedback service instance.

[0096] S250. Determine the target negative feedback service instance based on the weights of each instance.

[0097] S260. Send a negative feedback content query request to the target negative feedback service instance and obtain the negative feedback content determined by the target negative feedback service instance based on the user identifier.

[0098] The technical solution of this invention improves query efficiency by determining the target negative feedback service instance for the target user's negative feedback content query request. Furthermore, during the response process, when the target user is queried from the negative feedback user database, the negative feedback content query is performed on that target user, intercepting a large number of invalid requests and reducing system operating pressure. Querying the target user's negative feedback content based on the target user identifier improves query accuracy. Simultaneously, by updating the negative feedback user set cache in each negative feedback service instance via Redis broadcast, and querying whether the target user is a negative feedback user in the updated negative feedback user set cache based on the target user identifier, the accuracy of the query is further improved.

[0099] The following are embodiments of the negative feedback content determination device provided in this invention. This device and the negative feedback content determination method of the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the negative feedback content determination device, please refer to the embodiments of the negative feedback content determination method described above.

[0100] Example 3

[0101] Figure 3 This is a schematic diagram of the negative feedback content determination device provided in Embodiment 3 of the present invention. This embodiment is applicable to performance testing in software testing. The specific structure of the negative feedback content determination device is as follows: a negative feedback content query request acquisition module 310, a weight iteration coefficient determination module 320, an instance weight determination module 330, and a target negative feedback instance determination module 340; wherein...

[0102] The negative feedback content query request acquisition module 310 is used to acquire negative feedback content query requests for target users; wherein, the negative feedback content query request is generated based on a recommendation instruction or an application startup instruction, and the negative feedback content query request includes the user identifier of the target user;

[0103] The weight iteration coefficient determination module 320 is used to obtain the system parameters of each negative feedback service instance at the current time, and determine the weight iteration coefficient of each negative feedback service instance at the current time based on the system parameters.

[0104] The instance weight determination module 330 is used to determine the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient of each negative feedback service instance.

[0105] The target negative feedback instance determination module 340 is used to determine the target negative feedback service instance according to the weight of each instance, wherein the target negative feedback service instance is used to respond to the negative feedback content query request of the target user, obtain the query information of the negative feedback content, and output the query information of the negative feedback content;

[0106] The target negative feedback instance determination module 340 includes:

[0107] The negative feedback user determination submodule is used to determine whether the target user is a negative feedback user based on the user identifier;

[0108] The negative feedback content determination submodule is used to determine the negative feedback content of the target user based on the user identifier if the target user is a negative feedback user.

[0109] The technical solution of this invention specifically includes: acquiring a negative feedback content query request for a target user triggered by a recommendation instruction or an application launch instruction; obtaining negative feedback content query information for the target object based on the query request; acquiring system parameters of each negative feedback service instance at the current moment, determining the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters, and determining the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient; determining the negative feedback content query information for responding to the target user's negative feedback content query request based on the instance weights, obtaining the query information of the negative feedback content, and outputting the query information of the negative feedback content. A target negative feedback service instance is used to improve the efficiency of negative feedback content determination by identifying the highest-performing target negative feedback service instance among various negative feedback service instances. The method by which the target negative feedback service instance responds to the negative feedback content query request of the target user includes: determining whether the target user is a negative feedback user based on the user identifier; if the target user is a negative feedback user, then determining the target user's negative feedback content based on the user identifier. This achieves the interception of most invalid requests by the storage system, ensuring that only users with genuine negative feedback content query the negative feedback storage system, thus greatly reducing the load on the storage system and solving the performance bottleneck problem. The technical solution of this embodiment improves query efficiency by determining the target negative feedback service instance for the target user's negative feedback content query request, and during the response process, queries are performed on the target user based on the negative feedback user database to identify them as a negative feedback user, intercepting a large number of invalid requests and reducing the system's operational pressure. Simultaneously, querying the target user's negative feedback content based on the target user identifier improves the accuracy of the query.

[0110] Based on the above technical solution, the device also includes:

[0111] The database creation module is used to create a negative feedback content database and a negative feedback user database before obtaining a query request for negative feedback content from a target user.

[0112] The user and content acquisition module is used to acquire the negative feedback content and negative feedback user corresponding to any negative feedback operation when a negative feedback operation of any user is detected.

[0113] The database update module is used to update the negative feedback content database and the negative feedback user database based on the negative feedback content and the negative feedback user, respectively.

[0114] Based on the above technical solution, the device also includes:

[0115] The negative feedback user set update module is used to update the negative feedback content database and the negative feedback user database based on the negative feedback content and the negative feedback users respectively, and then broadcast the negative feedback user database to all negative feedback service instances based on Redis broadcast, thereby updating the negative feedback user set cache in each negative feedback service instance.

[0116] Based on the above technical solution, the negative feedback user determination submodule includes:

[0117] The user matching unit is used to match the user identifier with each negative feedback user identifier in the negative feedback user database.

[0118] The negative feedback user determination unit is used to determine the target user as a negative feedback user if a match is successful.

[0119] Based on the above technical solution, the system parameters of the negative feedback service instance include CPU load rate, memory usage rate, and service response time;

[0120] Accordingly, the expressions involved in the weight iteration coefficient determination module 320 include:

[0121]

[0122] in, represents the weight iteration coefficient, cpuLoadRate represents the CPU load rate, memoryUsage represents the memory usage rate, and rt represents the service response time.

[0123] Based on the above technical solution, the instance weight determination module 330 includes:

[0124] The instance weight determination unit is used to obtain the weight of the negative feedback service instance at the previous moment, update the weight at the previous moment based on the instance weight of the negative feedback service instance at the current moment, and obtain the instance weight of the negative feedback service instance at the current moment.

[0125] Based on the above technical solution, the target negative feedback instance determination module 340 includes:

[0126] The first target negative feedback instance determination unit is used to determine the negative feedback service instance corresponding to the largest instance weight as the target negative feedback service instance.

[0127] The second target negative feedback instance determination unit is used to determine the access probability of each negative feedback service instance based on the weight of each instance, and to determine the negative feedback service instance with the highest access probability as the target negative feedback service instance.

[0128] Based on the above technical solution, the device includes:

[0129] The recommendation request response module is used to determine the recommended content for the target user based on the negative feedback content and the user identifier, and to respond to the recommendation request of the target user.

[0130] The negative feedback content determination device provided in the embodiments of the present invention can execute the negative feedback content determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0131] It is worth noting that in the embodiments of the negative feedback content determination device described above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0132] Example 4

[0133] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A block diagram is shown of an exemplary electronic device 12 suitable for implementing embodiments of the present invention. Figure 4 The electronic device 12 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0134] like Figure 4 As shown, the electronic device 12 is represented in the form of a general-purpose computing electronic device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0135] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0136] Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0137] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 4 Not shown; usually referred to as a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0138] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0139] Electronic device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the electronic device 12, and / or with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, electronic device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 4 As shown, network adapter 20 communicates with other modules of electronic device 12 via bus 18. It should be understood that, although... Figure 4 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0140] Processing unit 16 executes various functional applications and acquires sample data by running programs stored in system memory 28, such as implementing the steps of a negative feedback content determination method provided in this embodiment, the negative feedback content determination method including:

[0141] Obtain a negative feedback content query request for the target user; wherein, the negative feedback content query request is generated based on a recommendation instruction or an application launch instruction, and the negative feedback content query request includes the user identifier of the target user;

[0142] Obtain the system parameters of each negative feedback service instance at the current moment, and determine the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters.

[0143] The instance weight of each negative feedback service instance at the current moment is determined based on the weight iteration coefficient of each negative feedback service instance.

[0144] The target negative feedback service instance is determined based on the weights of each instance, wherein the target negative feedback service instance is used to respond to the negative feedback content query request of the target user, obtain the query information of the negative feedback content, and output the query information of the negative feedback content.

[0145] The method by which the target negative feedback service instance responds to the target user's negative feedback content query request includes:

[0146] Based on the user identifier, determine whether the target user is a negative feedback user;

[0147] If the target user is a negative feedback user, then the negative feedback content of the target user is determined based on the user identifier.

[0148] Of course, those skilled in the art will understand that the processor can also implement the technical solution of the sample data acquisition method provided in any embodiment of the present invention.

[0149] Example 5

[0150] This fifth embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements, for example, the steps of a method for determining negative feedback content provided in this embodiment. The method for determining negative feedback content includes:

[0151] Obtain a negative feedback content query request for the target user; wherein, the negative feedback content query request is generated based on a recommendation instruction or an application launch instruction, and the negative feedback content query request includes the user identifier of the target user;

[0152] Obtain the system parameters of each negative feedback service instance at the current moment, and determine the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters.

[0153] The instance weight of each negative feedback service instance at the current moment is determined based on the weight iteration coefficient of each negative feedback service instance.

[0154] The target negative feedback service instance is determined based on the weights of each instance, wherein the target negative feedback service instance is used to respond to the negative feedback content query request of the target user, obtain the query information of the negative feedback content, and output the query information of the negative feedback content.

[0155] The method by which the target negative feedback service instance responds to the target user's negative feedback content query request includes:

[0156] Based on the user identifier, determine whether the target user is a negative feedback user;

[0157] If the target user is a negative feedback user, then the negative feedback content of the target user is determined based on the user identifier.

[0158] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: 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 this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0159] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0160] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0161] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including 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 it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0162] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0163] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for determining negative feedback content, applied to a recommendation system, characterized in that, include: Obtain a negative feedback content query request for the target user; wherein, the negative feedback content query request is generated based on a recommendation instruction or an application launch instruction, and the negative feedback content query request includes the user identifier of the target user; Obtain the system parameters of each negative feedback service instance at the current moment, and determine the weight iteration coefficient of each negative feedback service instance at the current moment based on the system parameters; The instance weight of each negative feedback service instance at the current moment is determined based on the weight iteration coefficient of each negative feedback service instance. The target negative feedback service instance is determined based on the weights of each instance, wherein the target negative feedback service instance is used to respond to the negative feedback content query request of the target user, obtain the query information of the negative feedback content, and output the query information of the negative feedback content. The method by which the target negative feedback service instance responds to the target user's negative feedback content query request includes: Based on the user identifier, determine whether the target user is a negative feedback user; If the target user is a negative feedback user, then the negative feedback content of the target user is determined based on the user identifier.

2. The method according to claim 1, characterized in that, Before obtaining the query request for negative feedback content from the target user, it also includes: Establish a negative feedback content database and a negative feedback user database; When a negative feedback action of any user is detected, obtain the negative feedback content and the negative feedback user corresponding to the negative feedback action. The negative feedback content database and the negative feedback user database are updated based on the negative feedback content and the negative feedback user, respectively.

3. The method according to claim 2, characterized in that, After updating the negative feedback content database and the negative feedback user database based on the negative feedback content and the negative feedback user respectively, the process further includes: The negative feedback user database is broadcast to all negative feedback service instances using Redis broadcast, and the negative feedback user set cache in each negative feedback service instance is updated.

4. The method according to claim 2, characterized in that, The step of determining whether the target user is a negative feedback user based on the user identifier includes: The user identifier is matched with each negative feedback user identifier in the negative feedback user database; If a match is successful, the target user is determined to be a negative feedback user.

5. The method according to claim 1, characterized in that, The system parameters of the negative feedback service instance include CPU load rate, memory usage rate, and service response time. Accordingly, the expression for determining the weight iteration coefficients of each negative feedback service instance at the current moment based on the system parameters includes: in, represents the weight iteration coefficient, cpuLoadRate represents the CPU load rate, memoryUsage represents the memory usage rate, and rt represents the service response time.

6. The method according to claim 1, characterized in that, The step of determining the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient of each negative feedback service instance includes: Obtain the weight of the negative feedback service instance at the previous moment, update the weight of the previous moment based on the instance weight of the negative feedback service instance at the current moment, and obtain the instance weight of the negative feedback service instance at the current moment.

7. The method according to claim 1, characterized in that, The step of determining the target negative feedback service instance based on the weights of each instance includes: The negative feedback service instance corresponding to the largest instance weight is determined as the target negative feedback service instance; or... Based on the weights of each instance, the access probability of each negative feedback service instance is determined, and the negative feedback service instance with the highest access probability is determined as the target negative feedback service instance.

8. The method according to claim 1, characterized in that, After determining the negative feedback content of the target user based on the user identifier, the method further includes: Based on the negative feedback content and the user identifier, the recommended content for the target user is determined, and the recommendation request for the target user is responded to.

9. A negative feedback content determination device, characterized in that, include: The negative feedback content query request acquisition module is used to acquire negative feedback content query requests for target users; wherein, the negative feedback content query request is generated based on a recommendation instruction or an application launch instruction, and the negative feedback content query request includes the user identifier of the target user; The weight iteration coefficient determination module is used to obtain the system parameters of each negative feedback service instance at the current time, and determine the weight iteration coefficient of each negative feedback service instance at the current time based on the system parameters. The instance weight determination module is used to determine the instance weight of each negative feedback service instance at the current moment based on the weight iteration coefficient of each negative feedback service instance; The target negative feedback instance determination module is used to determine the target negative feedback service instance according to the weight of each instance, wherein the target negative feedback service instance is used to respond to the negative feedback content query request of the target user, obtain the query information of the negative feedback content, and output the query information of the negative feedback content; The target negative feedback instance determination module includes: The negative feedback user determination submodule is used to determine whether the target user is a negative feedback user based on the user identifier; The negative feedback content determination submodule is used to determine the negative feedback content of the target user based on the user identifier if the target user is a negative feedback user.

10. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the negative feedback content determination method as described in any one of claims 1-8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the negative feedback content determination method as described in any one of claims 1-8.

Images