Data analysis method, device and electronic equipment

Abstract

The present disclosure relates to a data analysis method, device and electronic device, and relates to the field of data processing technology, and solves the problem of how to ensure the analysis of the advantages and disadvantages of two or more solutions while improving the efficiency of the analysis. The method includes: receiving an access request for accessing a target service sent by at least one electronic device; wherein the target service is provided by one or more business systems, and one business system operates independently through at least two different business solutions; performing the following operations on each electronic device: determining a target identifier corresponding to the access request according to the access request; determining the business solution used by each business system according to the target identifier; generating access data according to the business solution used by each business system; sending the access data to the electronic device; receiving feedback results of the access data sent by each electronic device; and determining the analysis results of the business solution according to the feedback results.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a data analysis method, device, and electronic device. Background Art

[0002] Currently, in the field of data processing technology, to test the same product function or achieve the same goal, two or more plans must be developed simultaneously. For example, two plans, Plan A and Plan B, must be developed. Operations and maintenance personnel then assign users to use Plan A and Plan B. They then analyze the pros and cons of Plan A and Plan B by collecting feedback from users of Plan A and those of Plan B.

[0003] When there are fewer solutions, the above operation can analyze the pros and cons of each solution, but the accuracy of the analysis depends on the diligence of the operations and maintenance personnel. When there are more solutions, a lot of manual work is required to assign users to different solutions. Operations and maintenance personnel then need to collect feedback from each user one by one to analyze the pros and cons of each solution, which results in low analysis efficiency.

[0004] Therefore, how to ensure the analysis of the pros and cons of two or more solutions while improving the efficiency of analysis has become an urgent problem to be solved. Summary of the Invention

[0005] In order to solve the above technical problems, the present disclosure provides a data analysis method, device and electronic device.

[0006] The technical solutions disclosed in this disclosure are as follows:

[0007] In a first aspect, the present disclosure provides a data analysis method, comprising: receiving an access request for accessing a target service sent by at least one electronic device; wherein the target service is provided by one or more business systems, and one business system operates independently through at least two different business solutions; performing the following operations for each electronic device: determining a target identifier corresponding to the access request based on the access request; determining the business solution used by each business system based on the target identifier; generating access data based on the business solution used by each business system; sending the access data to the electronic device; receiving feedback results on the access data sent by each electronic device; and determining an analysis result of the business solution based on the feedback results.

[0008] In a second aspect, the present disclosure provides a data analysis device, comprising: a receiving unit, configured to receive an access request for accessing a target service sent by at least one electronic device; wherein the target service is provided by one or more business systems, and a business system operates independently through at least two different business solutions; a processing unit, configured to perform the following operations for each electronic device: determining a target identifier corresponding to the access request based on the access request received by the receiving unit; determining the business solution used by each business system based on the target identifier; generating access data based on the business solution used by each business system; controlling the sending unit to send access data to the electronic device; the receiving unit, further configured to receive feedback results on the access data sent by each electronic device; and the processing unit, further configured to determine an analysis result of the business solution based on the feedback results received by the receiving unit.

[0009] In a third aspect, the present disclosure provides an electronic device comprising: a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement any one of the data analysis methods provided in the first aspect above when executing the computer program.

[0010] In a fourth aspect, the present disclosure provides a computer-readable storage medium, comprising: a computer program stored on the computer-readable storage medium, which, when executed by a computing device, enables the computing device to implement any one of the data analysis methods provided in the first aspect above.

[0011] In a fifth aspect, the present invention provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute any one of the data analysis methods provided in the first aspect.

[0012] It should be noted that the above-mentioned computer instructions may be stored in whole or in part on a first computer-readable storage medium. The first computer-readable storage medium may be packaged together with the processor of the data analysis device or separately from the processor of the data analysis device, and this disclosure does not limit this.

[0013] The descriptions of the second, third, fourth and fifth aspects in this disclosure can refer to the detailed description of the first aspect; and the beneficial effects of the descriptions of the second, third, fourth and fifth aspects can refer to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0014] In this disclosure, the names of the aforementioned data analysis devices do not limit the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this disclosure, they fall within the scope of the claims of this disclosure and their equivalents.

[0015] These and other aspects of the present disclosure will become more apparent from the following description.

[0016] The technical solution provided by the present disclosure has the following advantages compared with the existing technology:

[0017] When it is necessary to analyze the pros and cons of two or more solutions developed at the same time for the same product function or to achieve the same goal, an access request for accessing the target service is received from at least one electronic device; then, the following operations are performed for each electronic device: based on the access request, the target identifier corresponding to the access request is determined; based on the target identifier, the business solution used by each business system is determined; based on the business solution used by each business system, access data is generated; the access data is sent to the electronic device; feedback on the access data is received from each electronic device; and based on the feedback, the analysis results of the business solution are determined. In this way, the pros and cons of multiple solutions can be automatically evaluated. Since no human intervention is required, the accuracy of the pros and cons can be improved while ensuring the efficiency of the analysis. This solves the problem of how to ensure the analysis of the pros and cons of two or more solutions while improving the efficiency of the analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0019] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 This is a flow chart of a data analysis method according to an embodiment of the present application;

[0021] Figure 2 This is one of the structural schematic diagrams of the display device in the data analysis method provided in the embodiment of the present application;

[0022] Figure 3 This is a second structural diagram of a display device in the data analysis method provided in an embodiment of the present application;

[0023] Figure 4 This is a flow chart of a data analysis method according to an embodiment of the present application;

[0024] Figure 5 The second flowchart of the data analysis method provided in the embodiment of the present application;

[0025] Figure 6The third flowchart of the data analysis method provided in the embodiment of the present application;

[0026] Figure 7 This is a fourth flow chart of the data analysis method provided in an embodiment of the present application;

[0027] Figure 8 Flowchart 5 of the data analysis method provided in the embodiment of the present application;

[0028] Figure 9 A schematic diagram of the structure of the server provided in the embodiment of the present application;

[0029] Figure 10 A schematic diagram of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0031] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0032] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0033] In the embodiments of this disclosure, AB testing refers to developing two plans, A and B, to achieve the same product function or goal. A subset of users uses Plan A, while another subset uses Plan B. The effectiveness of Plans A and B is compared through user feedback, and the pros and cons of the two plans are evaluated through relevant data analysis.

[0034] The multi-layer ABTest system in the embodiment of the present disclosure means that a product function usually passes through multiple business systems before being finally presented to the user.

[0035] Figure 1 is a schematic diagram of an operation scenario between a display device and a control device according to one or more embodiments of the present application, such as Figure 1 As shown, a user can operate the display device 200 via a mobile terminal 300 and a control device 100. The control device 100 can be a remote controller, and communication between the remote controller and the display device includes infrared protocol communication, Bluetooth protocol communication, wireless or other wired methods to control the display device 200. The user can control the display device 200 by inputting user commands through buttons on the remote controller, voice input, control panel input, etc. In some embodiments, a mobile terminal, tablet computer, computer, laptop computer, and other smart devices can also be used to control the display device 200.

[0036] In some embodiments, the mobile terminal 300 can install software applications with the display device 200, and achieve connection and communication through a network communication protocol to achieve the purpose of one-to-one control operation and data communication. The audio and video content displayed on the mobile terminal 300 can also be transmitted to the display device 200 to achieve a synchronous display function. The display device 200 also communicates data with the display device 200 through various communication methods. The display device 200 can be allowed to communicate and connect through a local area network (LAN), a wireless local area network (WLAN) and other networks. The display device 200 can provide various content and interactions to the display device 200. The display device 200 can be a liquid crystal display, an OLED display, or a projection display device. In addition to providing a broadcast receiving television function, the display device 200 can also provide an intelligent network TV function that provides computer support functions.

[0037] In some embodiments, the electronic device provided by the embodiment of the present application can be the above-mentioned server 400. Among them, when it is necessary to analyze the advantages and disadvantages of two or more solutions formulated at the same time for the same product function or to achieve the same goal, the server 400 receives an access request for accessing the target service sent by at least one electronic device; thereafter, the server 400 performs the following operations for each electronic device: according to the access request, determine the target identifier corresponding to the access request; according to the target identifier, determine the business solution used by each business system; according to the business solution used by each business system, generate access data; send the access data to the electronic device; the server 400 receives the feedback results of the access data sent by each electronic device; the server 400 determines the analysis results of the business solution based on the feedback results. In this way, the server 400 can automatically complete the evaluation of the advantages and disadvantages of multiple solutions. Since no human participation is required, the accuracy of the advantages and disadvantages can be improved while ensuring the efficiency of the analysis.

[0038] Figure 2 FIG. 2 shows a hardware configuration block diagram of a display device 200 according to an exemplary embodiment. Figure 2 The display device 200 shown includes at least one of a tuner 210, a communicator 220, a detector 230, an external device interface 240, a controller 250, a display 260, an audio output interface 270, a memory, a power supply, and a user interface 280. The controller includes a central processing unit, a video processor, an audio processor, a graphics processor, RAM, ROM, and first to nth interfaces for input / output. The display 260 can be a display with touch functionality, such as a touch display. The tuner 210 receives broadcast television signals via wired or wireless reception, and demodulates audio and video signals, such as EPG data signals, from multiple wireless or wired broadcast television signals. The detector 230 is used to collect signals from the external environment or external interactions. The controller 250 and the tuner 210 can be located in different separate devices, that is, the tuner 210 can also be in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0039] In some embodiments, the controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in the memory. The controller 250 controls the overall operation of the display device 200.

[0040] In some examples, the display device 200 of one or more embodiments is a TV set 1, and the operating system of the TV set 1 is an Android system. Figure 3 As shown, the television 1 can be logically divided into an application layer (referred to as "application layer") 21, an application framework layer (referred to as "framework layer") 22, an Android runtime and system library layer (referred to as "system runtime library layer") 23, and a kernel layer 24.

[0041] Among them, the application layer 21 includes one or more applications. The application can be a system application or a third-party application. For example, the application layer 21 includes a first application, which can provide a fitness video playback function. The framework layer 22 provides an application programming interface (API) and a programming framework for the application program of the application layer 21. The system runtime layer 23 provides support for the upper layer, namely the framework layer 22. When the framework layer 22 is used, the Android operating system will run the C / C++ library contained in the system runtime layer 23 to implement the functions to be implemented by the framework layer 22. The kernel layer 24 serves as the software middleware between the hardware layer and the application layer 21, and is used to manage and control hardware and software resources.

[0042] In some examples, the kernel layer 24 includes a first driver and a second driver, the first driver is used to send the user operation collected by the detector 230 to the first application, and the second driver is used to control the display 260 to display the display information sent by the display unit 213.

[0043] The first application in the TV set 1 is started. The first application establishes a communication connection with the unit for providing communication services of the server 400 by calling the communicator 220. Afterwards, the first driver in the TV set 1 is used to send the user operation collected by the detector 230 to the first application for identification. Afterwards, in response to the user operation sent by the detector 230 (such as: the selection operation of the recommendation control), the first application sends an access request to the target service (such as obtaining recommended data) to the server 400. Afterwards, the receiving unit 401 of the server 400 receives the access request to the target service sent by the TV set 1. The processing unit 402 of the server 400 performs the following operations on the TV set 1: based on the access request received by the receiving unit 401, the target identifier corresponding to the access request is determined; based on the target identifier, the service scheme used by each service system is determined; based on the service scheme used by each service system, access data is generated; the processing unit 402 controls the sending unit 403 to send the access data to the TV set 1; and the receiving unit 401 of the server 400 receives the feedback result of the access data sent by the TV set 1. In this way, a feedback result of the access data corresponding to the target service of a TV set 1 can be obtained. Afterwards, the processing unit 402 of the server 400 analyzes the feedback result of the access data corresponding to the target service sent by one or more TV sets 1 received by the receiving unit 401, thereby determining the analysis result of the service solution.

[0044] Specifically, the electronic device provided in the embodiment of the present disclosure may be the above-mentioned display device 200 or the server 400, which is not limited here.

[0045] Specifically, the storage unit 404 of the server 400 is used to store one or more business systems providing services for the target service, one or more target thresholds corresponding to each business system, and data such as the operating system of the server 400 .

[0046] The access data, feedback results, length of stay, scoring results, and questionnaires involved in this application may be data authorized by the user or fully authorized by all parties.

[0047] In the following embodiments, the method of the embodiment of the present application is described by taking the execution entity of the data analysis method provided by the embodiment of the present disclosure as the above-mentioned server 400 and the electronic device as the television 1 as an example.

[0048] The present application embodiment provides a data analysis method, such as Figure 4 As shown, the data analysis method may include S11-S14.

[0049] S11. Receive an access request for a target service sent by at least one television set 1. The target service is provided by one or more service systems, and one service system operates independently through at least two different service solutions.

[0050] In some examples, after the TV 1 is turned on, the user can select the target service displayed on the TV 1. For example, when the target service is a recommended service, the TV 1 sends an access request to the server 400 in response to the selection of the recommended service control. Thus, after receiving the access request sent by the TV 1, the server 400 generates access data corresponding to the access request through one or more business systems that provide services for the recommended service. The server 400 then sends the access data to the TV 1, so that the TV 1 can display the access data corresponding to the recommended service. The TV 1 then collects user feedback on the access data and sends the feedback to the server 400. After receiving the feedback sent by the TV 1, the server 400 can obtain analysis results for each of the one or more business systems that provide services for the recommended service based on the feedback, so that better services can be provided to users during subsequent deployment.

[0051] In some examples, before the target service is finally displayed to the user, it needs to be jointly served by multiple business systems in order to provide the target service to the user. For example, if the target service is to obtain recommendation information through a recommendation system, the process of the recommendation system recommending personalized content to the user will go through multiple business systems such as recall, rough sorting, fine sorting, and re-sorting, and each business system will have a different implementation plan. In order to ensure that the business plan of each business system can be reasonably allocated to the TV 1 that executes the business plan, the data analysis method provided by the embodiment of the present disclosure, after receiving the access request sent by the TV 1 to access the target service, randomly generates a random number and uses the random number as the target identifier of the access request. In this way, by comparing the target identifier with the target threshold of each business system, the business plan used by each business system can be determined. Alternatively, according to the time sequence of the received access requests, the same number of TVs 1 are sequentially allocated to each business method of each business system to execute the business plan. Alternatively, according to a preset cycle, a set of business plans in the business system is executed in the current preset cycle, and another set of business plans in the business system is executed in the next preset cycle, and the cycle stops after each set of business plans in the business system is executed.

[0052] S12. For each TV 1, perform the following operations: determine the target identifier corresponding to the access request according to the access request; determine the service scheme used by each service system according to the target identifier; generate access data according to the service scheme used by each service system; and send the access data to the TV 1.

[0053] In some examples, after receiving an access request to a target service sent by TV 1, a random number is randomly generated and used as the target identifier of the access request. Alternatively, according to the time sequence of the received access requests, the same number of TVs 1 are sequentially assigned to each set of business methods of each business system to execute the business plan. At this time, the target identifiers corresponding to the access requests for executing the same set of business plans are the same, and the target identifiers corresponding to the business plans of different business systems are different. Alternatively, according to a preset cycle, a set of business plans in the business system is executed in the current preset cycle, and another set of business plans in the business system is executed in the next preset cycle, until each set of business plans in the business system is executed and the cycle stops. The target identifiers corresponding to the access requests for executing the business plans of the same business system in the same preset cycle are the same.

[0054] In some examples, different business solutions in different business systems correspond to different target identifiers. After determining the target identifier corresponding to the access request, the preset relationship (including the corresponding relationship between different business solutions and target identifiers in different business systems) can be queried based on the target identifier to determine the business solution used in each business system. For example, when the target service is provided by one business system, only one target identifier needs to be determined, and then the business solution corresponding to the target identifier is determined by querying the preset relationship. When the target service is provided by multiple business systems, multiple target identifiers need to be determined, and then the business solution used by each business system is determined by querying the preset relationship.

[0055] Alternatively, the target identifier is a random number, and the business plan used by each business system is determined by comparing the size relationship between the target identifier and the target threshold. For example, when only one business system provides services for the target service, assuming that the value range of the random number α is between (0, 1), the business system has two business plans, planA and planB, and 90% and 10% of the traffic needs to be split for planA and planB respectively to perform ABTest, that is, the target threshold epsilon can be 0.9 or 0.1. For each TV 1, when an access request to the target service sent by TV 1 is received, a random number α between (0, 1) is generated, and then it is determined whether α>epsilon is true. If α>epsilon, planA is used to generate access data and send it to TV 1. If α≤epsilon, planB is used to generate access data and send it to TV 1. As you can see, since α is a random number between (0, 1) generated when TV 1 receives an access request to the target service, when epsilon is 0.1, the probability that α > epsilon is 90%. This means that for each access request sent by TV 1 to the target service, there is a 90% probability that Plan A will be used, and a 10% probability that Plan B will be used. This ensures that 90% of the traffic will be diverted to Plan A and 10% to Plan B, respectively, thus implementing the traffic diversion mechanism of our ABTest system.

[0056] Alternatively, four business systems provide services for the target service. Assume that the random number α ranges from (0 to 1), and each business system contains only two business solutions. Business system 1 uses solutions 1-1 and 1-2, respectively; business system 2 uses solutions 2-1 and 2-2, respectively; business system 3 uses solutions 3-1 and 3-2, respectively; and business system 4 uses solutions 4-1 and 4-2. For a system that requires simultaneous AB testing at different levels, we define a corresponding target threshold, epsilon_i, based on the traffic diversion requirements of different business systems, where the subscript i represents the corresponding business system. For example, epsilon_1, epsilon_2, epsilon_3, and epsilon_4. In business system 1, we generate a random number α_1 between (0, 1), then compare α_1 with epsilon_1 to determine which business solution of business system 1 (such as business solution 1-1) to offload the current method request to. The output generated by business solution 1-1 is then input into business system 2. After receiving the output from business system 1, business system 2 regenerates a new random number α_2 between (0, 1), compares α_2 with epsilon_2, determines which business solution of business system 2 (such as business solution 2-1) to offload the current method request to, and inputs the output generated by business solution 2-1 into business system 3 as input. After receiving the output from business system 2, business system 3 regenerates a new random number α_3 between (0, 1), compares α_3 with epsilon_3, and determines which business solution (e.g., business solution 3-1) of business system 3 to direct the current method request to. The output generated by business solution 3-1 is then input to business system 4. After receiving the output from business system 3, business system 4 regenerates a new random number α_4 between (0, 1), compares α_4 with epsilon_4, and determines which business solution (e.g., business solution 4-1) of business system 4 to direct the current method request to, generating the final access data. It can be seen that in the ABTest system, the adjustment of the input of the previous business system has exactly the same impact on all business systems at the next level. That is to say, if the parameters of the previous business system are adjusted or the plan of the previous business system is replaced, the impact on subsequent business systems is completely consistent, and will not affect the data comparison between different business plans of the next business system. Therefore, there is no need to consider the interference of the adjustment of the previous business system on the ABTest data of the next level. Similarly, the adjustment of the next business system will not interfere with the ABTest data of the previous business system, thereby achieving independence between ABTests at different levels.

[0057] Alternatively, the same business system contains three or more service plans, such as Plan A, Plan B, and Plan C, which need to be compared online simultaneously. The plan is to divert 85%, 10%, and 5% of the traffic to each of these plans, respectively. In this case, we only need to define two target thresholds, epsilon_1 and epsilon_2, with values ​​of 0.1 and 0.05, respectively. Upon receiving each access request from TV 1 to the target service, we generate a random number α between (0, 1) and first compare whether α > epsilon_1 + epsilon_2. If α > epsilon_1 + epsilon_2, plan A is used. Otherwise, we continue to check whether α > epsilon_2. If α > epsilon_2, plan B is used, otherwise plan C is used. This allows us to divert 85%, 10%, and 5% of the traffic to plan A, plan B, and plan C, respectively. Finally, we can compare the online performance of the three plans based on log statistics and data analysis, thus enabling simultaneous A / B testing of multiple plans.

[0058] Alternatively, by setting an interval range for different business solutions of different business systems, and then querying the preset relationship between the interval range and the business solution, the interval range into which the target identifier falls can be determined, and then the business solution used by the current business system can be determined based on the interval range.

[0059] For example, there are two business systems that provide services for the target service, namely business system 1 and business system 2. Business system 1 includes two sets of business plans, namely business plan 1 and business plan 2. Business system 2 includes two sets of business plans, namely business plan 3 and business plan 4. The preset relationship is shown in Table 1.

[0060] Table 1

[0061]

[0062] Afterwards, after receiving the access request sent by TV 1, server 400 randomly generates a random number, such as 0.8. Since the order of the business systems providing services for the target service is business system 1 and business system 2. At this time, it can be seen from querying Table 1 that 0.8 falls into the interval range of (0.1, 1] of business system 1. Therefore, it can be determined that the business solution used by business system 1 is business solution 2. Afterwards, business system 1 sends the obtained processing result to business system 2. After receiving the processing result sent by business system 1, business system 2 re-randomly generates a random number, such as 0.5. At this time, it can be seen from querying Table 1 that 0.5 falls into the interval range of [0, 0.8] of business system 2. Therefore, it can be determined that the business solution used by business system 2 is business solution 1.

[0063] In some examples, access data is generated based on the business solution used by each business system. For example, when the target service is a recommendation service, the systems providing services for the recommendation service include a recall system, a rough ranking system, a fine ranking system, and a re-ranking system. The recommendation request needs to be input into the recall system, and the recall system will generate a recall result. Afterwards, the recall system sends the recall result to the rough ranking system, and the rough ranking system generates a rough ranking result based on the recall result. Afterwards, the rough ranking system sends the rough ranking result to the fine ranking system. The fine ranking system generates a fine ranking result based on the rough ranking result. Afterwards, the fine ranking system sends the fine ranking result to the re-ranking system. The re-ranking system generates the final access data (such as recommendation data) based on the fine ranking result. In this way, different televisions 1 can generate different access data through different business solutions in the same business system. When the television 1 displays the access data, the user can determine whether it meets the user's recommendation needs based on the data displayed by the television 1. For example, by displaying a questionnaire on the television 1, the user's feedback on the access data can be obtained. For example, if the target service is only provided by one business system, the television 1 can prompt the user to open the questionnaire control while displaying the access data. The questionnaire control displays a scoring option control for the user's satisfaction with the current access data. Then, in response to the selection of the scoring option control, the television 1 uploads the scoring result to the server 400. The server 400 determines the feedback result based on the scoring result. For example, if the score in the scoring result is greater than 90 points, the feedback result is considered excellent; if the score in the scoring result is less than or equal to 90 points and greater than or equal to 75 points, the feedback result is considered good, etc. In this way, the user's feedback on the access data can be obtained.

[0064] When the target service is provided by only a plurality of business systems, if the plurality of business systems respectively provide data of different modules in the access data (such as a film module, a children's module, a news module, etc.), the television set 1 can prompt the user to open a questionnaire control in the process of displaying the access data, and the questionnaire control displays a scoring option control for the satisfaction level of each module in the current access data. Afterwards, the television set 1 responds to the selection operation of the scoring option control and uploads the scoring result to the server 400. The server 400 determines the feedback result based on the scoring result. For example, if the score in the scoring result of the film module is greater than 90 points, the feedback result of the film module is considered to be excellent. If the score in the scoring result of the children's module is less than or equal to 90 points and greater than or equal to 75 points, the feedback result of the children's module is considered to be good. In this way, the user's feedback result on each business system of the access data can be obtained.

[0065] Alternatively, when the target service is provided by only multiple business systems, and the multiple business systems work together to generate access data, the TV 1 can prompt the user to open a questionnaire control while displaying the access data. The questionnaire control displays a scoring option control for the satisfaction level of the current access data. Afterwards, the TV 1 uploads the scoring result to the server 400 in response to the selection operation of the scoring option control. The server 400 determines the feedback result based on the scoring result. For example, if the score in the scoring result is greater than 90 points, the feedback result of each business system that generated the access data corresponding to the feedback result is determined to be excellent; if the score in the scoring result is less than or equal to 90 points and greater than or equal to 75 points, the feedback result of each business system that generated the access data corresponding to the feedback result is determined to be good, etc. In this way, the user's feedback result on the access data can be obtained.

[0066] Alternatively, user feedback on the access data can be obtained based on the duration of time the user remains on TV 1 while the access data is displayed on TV 1. For example, at 11:06:04 AM on October 12, 2022, TV 1 sends an access request to the target service to server 400. Subsequently, at 11:06:20 AM on October 12, 2022, server 400 sends the access data to TV 1. Subsequently, at 10:06:09 AM on October 13, 2022, TV 1 again sends an access request to the target service to server 400. At this point, when TV 1 displays access data after 11:06:20 AM on October 12, 2022, the user can select and view the displayed access data. In this case, TV 1 uses the viewing duration as the dwell time. By counting the viewing time of the access data played by TV 1 between 11:06:20 on October 12, 2022 and 10:06:09 on October 13, 2022, the stay time corresponding to the access request sent by the server 400 at 11:06:20 on October 12, 2022 is obtained.

[0067] S13: Receive feedback results of access data sent by each TV set 1.

[0068] S14. Determine the analysis results of the business plan based on the feedback results.

[0069] In some examples, when there is only one business system providing services for the target service, the analysis results of the business plan can be determined directly based on each feedback result, such as: the business system includes two business plans, namely planA and planB. At this time, after the above-mentioned processes of S11 and S12, different televisions 1 are assigned to different business plans, such as the access data generated according to planA, or the access data generated according to planB. Since the access data generated by different business plans are different, the feedback results of the access data generated according to planA and the feedback results of the access data generated according to planB are analyzed, such as: determining the total number of target evaluation results (such as excellent, good) in the feedback results of the access data generated according to planA, and comparing it with the total number of target evaluation results (such as excellent, good) in the feedback results of the access data generated according to planB. When the total number of target evaluation results (such as excellent, good) in the feedback results of the access data generated according to planA is greater than the total number of target evaluation results (such as excellent, good) in the feedback results of the access data generated according to planB, it is determined that the analysis result of the business plan is that planA is better than planB. If the total number of target evaluation results (e.g., excellent, good) in the feedback results of access data generated based on planA is equal to the total number of target evaluation results (e.g., excellent, good) in the feedback results of access data generated based on planB, the business plan analysis result is determined to be equally excellent. If the total number of target evaluation results (e.g., excellent, good) in the feedback results of access data generated based on planA is less than the total number of target evaluation results (e.g., excellent, good) in the feedback results of access data generated based on planB, the business plan analysis result is determined to be superior to planA.

[0070] When multiple business systems provide services for a target service, in one case, the feedback results include evaluation results for each business system (e.g., different business systems provide different access data). In this case, the same operation process can be performed on each business system based on the process of determining the analysis results of the business plan when only one business system provides services for the target service, thereby determining the analysis results of each business plan. For example, there are two business systems providing services for the target service, namely business system 1 and business system 2. Business system 1 is used to provide film and television recommendations, and business system 2 is used to recommend content through news. Business system 1 includes two business plans, namely business plan 1-1 and business plan 1-2, and business system 2 includes two business plans, namely business plan 2-1 and business plan 2-2. In this case, after the above-mentioned processes S11 and S12, different televisions 1 are assigned to different business plans, such as the access data generated by business plan 1-1 and business plan 2-1, business plan 1-1 and business plan 2-2, business plan 1-2 and business plan 2-1, and business plan 1-2 and business plan 2-2, respectively. The feedback results corresponding to the access data of business plan 1-1 and business plan 2-1, business plan 1-1 and business plan 2-2, business plan 1-2 and business plan 2-1, and business plan 1-2 and business plan 2-2 include the evaluation results of each business system. At the same time, different business plans generate different access data. Therefore, the feedback results of the access data generated by business plan 1-1 and business plan 2-1, business plan 1-1 and business plan 2-1, business plan 1-2 and business plan 2-1, and business plan 1-2 and business plan 2-2 are analyzed, such as: determining the access data generated by business plan 1-1 and business plan 2-1, and business plan 1-1 and business plan 2-2. The total number of target evaluation results (e.g., excellent, good) for business plan 1-1 in the feedback results of the access data generated by business plan 1-2 and business plan 2-1, and business plan 1-2 and business plan 2-2, the total number of target evaluation results (e.g., excellent, good) for business plan 2-1 in the feedback results of the access data generated by business plan 1-1 and business plan 2-1, and business plan 1-2 and business plan 2-1, and the total number of target evaluation results (e.g., excellent, good) for business plan 2-2 in the feedback results of the access data generated by business plan 1-1 and business plan 2-2, and business plan 1-2 and business plan 2-2. When the total number of target evaluation results (e.g., excellent, good) for business plan 1-1 is greater than the total number of target evaluation results (e.g., excellent, good) for business plan 1-2, the business plan analysis result is determined to be that business plan 1-1 is superior to business plan 1-2.When the total number of target evaluation results (e.g., excellent, good) for business plan 1-1 equals the total number of target evaluation results (e.g., excellent, good) for business plan 1-2, the business plan analysis result is determined to be equally excellent. When the total number of target evaluation results (e.g., excellent, good) for business plan 1-1 is less than the total number of target evaluation results (e.g., excellent, good) for business plan 1-2, the business plan analysis result is determined to be superior to business plan 1-1. Similarly, when the total number of target evaluation results (e.g., excellent, good) for business plan 2-1 is greater than the total number of target evaluation results (e.g., excellent, good) for business plan 2-2, the business plan analysis result is determined to be superior to business plan 2-2. When the total number of target evaluation results (e.g., excellent, good) for business plan 2-1 equals the total number of target evaluation results (e.g., excellent, good) for business plan 2-2, the business plan analysis result is determined to be equally excellent to business plan 2-1 and business plan 2-2. When the total number of target evaluation results (such as excellent, good) of business plan 2-1 is less than the total number of target evaluation results (such as excellent, good) of business plan 2-2, the analysis result of the business plan is determined to be that business plan 2-2 is better than business plan 2-1.

[0071] In another case, the feedback result includes only one overall evaluation result. In this case, the overall evaluation result is used as the feedback result for each set of business plans that generated the access data corresponding to the overall feedback result. For example, there are two business systems providing services for the target service, namely business system 1 and business system 2. Business system 1 includes two business plans, namely business plan 1-1 and business plan 1-2, and business system 2 includes two business plans, namely business plan 2-1 and business plan 2-2. In this case, after the above-mentioned processes S11 and S12, different televisions 1 are assigned to different business plans. For example, based on the access data generated by business plan 1-1 and business plan 2-1, business plan 1-1 and business plan 2-2, business plan 1-2 and business plan 2-1, and business plan 1-2 and business plan 2-2, and the overall evaluation result of the access data corresponding to business plan 1-1 and business plan 2-1 is the target evaluation result (such as excellent or good), then the feedback result corresponding to business plan 1-1 is also the target evaluation result, and the feedback result corresponding to business plan 2-1 is also the target evaluation result. The process for determining the feedback results corresponding to the access data for Business Plan 1-1 and Business Plan 2-2, Business Plan 1-2 and Business Plan 2-1, and Business Plan 1-2 and Business Plan 2-2 is similar to the process for determining the feedback results corresponding to the access data for Business Plan 1-1 and Business Plan 2-1, and will not be repeated here. Subsequently, because different business plans generate different access data, the feedback results of the access data generated by Business Plan 1-1 and Business Plan 2-1, Business Plan 1-1 and Business Plan 2-1, Business Plan 1-2 and Business Plan 2-1, and Business Plan 1-2 and Business Plan 2-2 are analyzed. For example, the feedback result for Business Plan 1-1 is the total number of target evaluation results (e.g., excellent, good), the feedback result for Business Plan 1-2 is the total number of target evaluation results (e.g., excellent, good), the feedback result for Business Plan 2-1 is the total number of target evaluation results (e.g., excellent, good), and the feedback result for Business Plan 2-2 is the total number of target evaluation results (e.g., excellent, good). When the total number of target evaluation results (e.g., excellent, good) for business plan 1-1 equals the total number of target evaluation results (e.g., excellent, good) for business plan 1-2, the business plan analysis result is determined to be equally excellent. When the total number of target evaluation results (e.g., excellent, good) for business plan 1-1 is less than the total number of target evaluation results (e.g., excellent, good) for business plan 1-2, the business plan analysis result is determined to be superior to business plan 1-1. Similarly, when the total number of target evaluation results (e.g., excellent, good) for business plan 2-1 is greater than the total number of target evaluation results (e.g., excellent, good) for business plan 2-2, the business plan analysis result is determined to be superior to business plan 2-2.If the total number of target evaluation results (e.g., excellent, good) for business plan 2-1 is equal to the total number of target evaluation results (e.g., excellent, good) for business plan 2-2, the business plan analysis result is determined to be equally excellent. If the total number of target evaluation results (e.g., excellent, good) for business plan 2-1 is less than the total number of target evaluation results (e.g., excellent, good) for business plan 2-2, the business plan analysis result is determined to be superior to business plan 2-1.

[0072] As can be seen from the above, the analysis method provided by the embodiment of the present disclosure, when it is necessary to analyze the pros and cons of two or more solutions formulated at the same time for the same product function or to achieve the same goal, the server 400 receives an access request for accessing the target service sent by at least one television 1; thereafter, the server 400 performs the following operations for each electronic device: the server 400 determines the target identifier corresponding to the access request based on the access request; the server 400 determines the business solution used by each business system based on the target identifier; the server 400 generates access data based on the business solution used by each business system; the server 400 sends the access data to the television 1; receives the feedback result of the access data sent by each television 1; and determines the analysis result of the business solution based on the feedback result. In this way, the pros and cons of multiple solutions can be automatically evaluated. Since no human intervention is required, the accuracy of the pros and cons can be improved while ensuring the efficiency of the analysis.

[0073] In some possible implementations, combining Figure 4 ,like Figure 5 As shown, the above S12 can be specifically implemented through the following S120.

[0074] S120. Perform the following operations for each TV 1: randomly generate a random number based on the access request, and use the random number as the target identifier corresponding to the access request; determine the service plan used by each service system based on the target identifier; generate access data based on the service plan used by each service system; and send the access data to the TV 1.

[0075] In some examples, when an access request is received, a random number can be randomly generated, the remainder of the random number can be taken, and the remainder can be used as the target identifier corresponding to the access request. Alternatively, when an access request is received, a random number between 0 and 1 can be randomly generated, and the random number can be used as the target identifier corresponding to the access request. This ensures that the television 1 can be randomly assigned to the service plan of each service system, avoids access data inconsistencies caused by user differences, and improves the accuracy of analysis results.

[0076] In some feasible examples, the random number is greater than or equal to 0 and less than or equal to 1.

[0077] In some examples, the computing resource occupation of server 400 is reduced. The data analysis method provided by the embodiment of the present disclosure randomly generates a random number between 0 and 1, so that when determining the business plan used by each business system based on the random number, smaller computing resources can be occupied to ensure the normal operation of server 400.

[0078] In some feasible examples, a business system corresponds to one or more target thresholds, the target identifier includes one or more sub-identifiers, and one sub-identifier corresponds to a business system; Figure 4 ,like Figure 6 As shown, the above S12 can be specifically implemented through the following S121.

[0079] S121. For each TV 1, perform the following operations: determine the target identifier corresponding to the access request based on the access request; perform the following operations for each business system: determine the business plan used by the business system based on the sub-identifier and target threshold corresponding to the business system; generate access data based on the business plan used by each business system; and send the access data to the TV 1.

[0080] In some examples, when only one business system is included to provide services for the target service, the target identifier is equal to the sub-identifier. When multiple business systems are included to provide services for the target range, a sub-identifier needs to be generated for each business system so as to determine the business solution used by the business system based on the sub-identifier and the target threshold corresponding to the business system. For example, the business systems that provide services for the target range include two business systems, namely business system 1 and business system 2. At this time, the server 400 needs to generate a sub-identifier 1 for business system 1, and then generate a sub-identifier 2 for business system 2. Afterwards, the server 400 determines the business solution used by business system 1 based on the sub-identifier 1 and the target threshold corresponding to business system 1. Similarly, the server 400 determines the business solution used by business system 2 based on the sub-identifier 2 and the target threshold corresponding to business system 2.

[0081] It should be noted that the process of server 400 determining the business plan used by business system 1 based on sub-identifier 1 and the target threshold corresponding to business system 1, or the process of server 400 determining the business plan used by business system 2 based on sub-identifier 2 and the target threshold corresponding to business system 2, is the same as the process of determining the business plan used by each business system based on the target identifier in S12 above, and will not be repeated here.

[0082] In some possible implementation examples, combined with Figure 6 ,like Figure 7 As shown, the above S121 can be specifically implemented through the following S1210.

[0083] S1210: For each television 1, the following operations are performed: based on the access request, a target identifier corresponding to the access request is determined. For each service system, the following operations are performed: based on the magnitude relationship between the sub-identifier corresponding to the service system and the target threshold, a service scheme used by the service system is determined; access data is generated based on the service scheme used by each service system; and the access data is sent to the television 1.

[0084] It should be noted that the process by which the server 400 determines the business plan used by the business system based on the size relationship between the sub-identifier corresponding to the business system and the target threshold is similar to the process of determining the business plan used by each business system based on the target identifier in the above S12, and will not be repeated here.

[0085] In some feasible examples, a difference between the total number of business solutions included in the business system and the total number of target thresholds included in the business system is equal to 1.

[0086] In some feasible examples, a set of business solutions corresponds to a set of business identifiers, and the feedback result includes the business solution adopted by the access data corresponding to the feedback result; Figure 4 ,like Figure 8 As shown, the above S14 can be specifically implemented through the following S140.

[0087] S140 : Determine an analysis result of the business plan according to the total number of target evaluation results corresponding to the business identifier corresponding to the business plan in each feedback result.

[0088] It should be noted that the process by which the server 400 determines the analysis results of the business plan based on the total number of target evaluation results corresponding to the business identifier corresponding to the business plan in each feedback result is similar to the process of determining the analysis results of the business plan based on the feedback results in S14 above, and will not be repeated here.

[0089] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of method. In order to realize the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily appreciate that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0090] The embodiment of the present application can divide the functional modules of the data analysis device according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0091] like Figure 9 As shown, an embodiment of the present application provides a structural diagram of a server 400 , which includes a communicator 101 and a processor 102 .

[0092] The communicator 101 is used to receive an access request for accessing a target service sent by at least one electronic device; wherein the target service is provided by one or more business systems, and one business system operates independently through at least two different business solutions; the processor 102 is used to perform the following operations for each electronic device: determining the target identifier corresponding to the access request based on the access request received by the communicator 101; determining the business solution used by each business system based on the target identifier; generating access data based on the business solution used by each business system; controlling the communicator 101 to send the access data to the electronic device; the communicator 101 is also used to receive feedback results on the access data sent by each electronic device; the processor 102 is also used to determine the analysis results of the business solution based on the feedback results received by the communicator 101.

[0093] In some feasible examples, the processor 102 is specifically configured to randomly generate a random number according to the access request received by the communicator 101, and use the random number as a target identifier corresponding to the access request.

[0094] In some feasible examples, the random number is greater than or equal to 0 and less than or equal to 1.

[0095] In some feasible examples, a set of business systems corresponds to one or more target thresholds, the target identifier includes one or more sub-identifiers, and one sub-identifier corresponds to a set of business systems; the processor 102 is specifically used to perform the following operations for each set of business systems: determine the business plan used by the business system based on the sub-identifier and target threshold corresponding to the business system.

[0096] In some feasible examples, the processor 102 is specifically configured to determine a service solution used by the service system according to a magnitude relationship between a sub-identifier corresponding to the service system and a target threshold.

[0097] In some feasible examples, a difference between the total number of business solutions included in the business system and the total number of target thresholds included in the business system is equal to 1.

[0098] In some feasible examples, a set of business solutions corresponds to a set of business identifiers, and the feedback result includes the business solution adopted by the access data corresponding to the feedback result; the processor 102 is specifically used to determine the analysis result of the business solution based on the total number of target evaluation results corresponding to the business identifier corresponding to the business solution in each feedback result.

[0099] Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and its role will not be repeated here.

[0100] Of course, the server 400 provided in the embodiment of the present application includes but is not limited to the above modules. For example, the server 400 may further include a memory 103. The memory 103 may be used to store program codes of the server 400 and data generated by the server 400 during operation, such as data in a write request.

[0101] As an example, combining Figure 3 The functions implemented by the receiving unit 401 and the sending unit 403 in the server 400 are the same as those of the communicator 101, the functions implemented by the processing unit 402 are the same as those of the processor 103, and the functions implemented by the storage unit 404 are the same as those of the memory 103.

[0102] like Figure 10 As shown, an embodiment of the present application further provides a chip system, which can be applied to the server 400 in the aforementioned embodiment. The chip system includes at least one processor 1501 and at least one interface circuit 1502. The processor 1501 can be the processor in the above-mentioned server 400. The processor 1501 and the interface circuit 1502 can be interconnected via a line. The processor 1501 can receive and execute computer instructions from the memory of the above-mentioned server 400 through the interface circuit 1502. When the computer instructions are executed by the processor 1501, the server 400 can execute the various steps performed by the server 400 in the above-mentioned embodiment. Of course, the chip system can also include other discrete components, which are not specifically limited in this embodiment of the present application.

[0103] The embodiment of the present application also provides a computer-readable storage medium for storing computer instructions executed by the above-mentioned server 400.

[0104] The embodiment of the present application also provides a computer program product, including computer instructions executed by the above-mentioned server 400.

[0105] The foregoing description is intended only to provide specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. 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 the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein, but rather to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A data analysis method, characterized in that: include: Receiving an access request for accessing a target service sent by at least one electronic device; wherein the target service is provided by multiple business systems, each business system independently operates through at least two different business solutions, each business system corresponds to one or more target thresholds, the difference between the total number of business solutions included in the business system and the total number of target thresholds included in the business system is equal to 1, and one sub-identifier corresponds to one business system; For each access request of the electronic device, the following operations are performed: for each business system, a random number is randomly generated according to the access request, and the random number is used as the sub-identifier corresponding to the business system; based on the sub-identifier corresponding to the business system and the target threshold, the business scheme used by the business system is determined; access data is generated according to the business scheme used by each business system; and the access data is sent to the electronic device, where the access data is generated based on the joint action of the multiple business systems; receiving feedback results of the access data sent by each electronic device; According to the feedback result, an analysis result of a combination of the business solutions of the multiple business systems corresponding to the access data is determined.

2. The data analysis method according to claim 1, characterized in that The random number is greater than or equal to 0 and less than or equal to 1.

3. The data analysis method according to claim 1, wherein: The determining, based on the sub-identifier and target threshold corresponding to the business system, a business solution used by the business system includes: The service solution used by the service system is determined according to the magnitude relationship between the sub-identifier corresponding to the service system and the target threshold.

4. The data analysis method according to claim 1, wherein: A set of business schemes corresponds to a set of business identifiers, and the feedback result includes the business scheme adopted by the access data corresponding to the feedback result; Determining the analysis result of the business plan based on the feedback result includes: The analysis result of the business solution is determined according to the total number of target evaluation results corresponding to the business identifier corresponding to the business solution in each feedback result.

5. A data analysis device, characterized in that: include: a receiving unit, configured to receive an access request for accessing a target service sent by at least one electronic device; wherein the target service is provided by one or more business systems, each business system independently operates through at least two different business solutions, each business system corresponds to one or more target thresholds, the difference between the total number of business solutions included in the business system and the total number of target thresholds included in the business system is equal to 1, and one sub-identifier corresponds to one business system; The processing unit is configured to perform the following operations for each access request of the electronic device: for each business system, randomly generate a random number based on the access request, and use the random number as a sub-identifier corresponding to the business system; determine the business plan used by the business system based on the sub-identifier corresponding to the business system and a target threshold; generate access data based on the business plan used by each business system; and control a sending unit to send the access data to the electronic device, where the access data is generated based on the joint action of the multiple business systems; The receiving unit is further configured to receive feedback results on the access data sent by each electronic device; The processing unit is further configured to determine, based on the feedback result received by the receiving unit, an analysis result of a combination of the access data and the business solutions of the multiple business systems.

6. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the data analysis method according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that include: The computer-readable storage medium stores a computer program, and when the computer program is executed by a computing device, the computing device implements the data analysis method according to any one of claims 1 to 4.

Images