[0022] In order to make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, those of ordinary skill in the art can appreciate that, in the various embodiments of the present invention, many technical details are set forth in order for the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can be realized. The following divisions of the various embodiments are for the convenience of description, and should not constitute any limitation on the specific implementation of the present invention, and the various embodiments may be combined with each other and referred to each other on the premise of not contradicting each other.
[0023] The first embodiment of the present invention relates to a method for evaluating a binding process. The method for evaluating a binding process in this embodiment is applied to a server, but not limited to this. The method for evaluating a binding process in this embodiment can evaluate intelligent hardware. Smart hardware involves lighting systems, security systems, energy and environmental systems, entertainment audio-visual systems, home appliance kitchen and bathroom systems, sports health systems, etc., including but not limited to smart sockets, smart switches, smart lights, gateways, door locks, remote controls, dehumidifiers , air conditioners, air purifiers, fresh fans, humidifiers, air detectors, electric heaters, electric fans, thermostats, sensors, alarms, integrated stoves, refrigerators, kettles, rice cookers, water purifiers, water dispensers, beverage dispensers , range hood, induction cooker, pressure cooker, dishwasher, speaker, game console, TV, alarm clock, smart toilet, Yuba, washing machine, dryer, robot vacuum cleaner, water heater, clothes drying rack, curtain, blood pressure monitor, oximeter , weight and body fat scales, watches, electric toothbrushes, thermometers, etc. Terminals bound to smart hardware include but are not limited to mobile phones, tablet computers, etc.
[0024] The method for evaluating a binding process in this embodiment includes: acquiring binding data from each terminal, wherein the binding data includes: behavior data used by each user to bind hardware and hardware information of the bound hardware; The binding data determines the target behavior data for the user to bind the target hardware; the target behavior data is input into a pre-built hardware binding evaluation model to obtain a hardware binding evaluation index; wherein, the hardware binding evaluation model is used to evaluate the target hardware. The behavior data is counted, and the hardware binding evaluation index is used to evaluate the hardware binding process. In this embodiment, the binding data is obtained from each terminal, and a large number of statistical samples can be obtained. The collected data comes from the terminal, the data is objective and accurate, and no manual data collection is required, which reduces the demand for human resources and time resources for data collection. The data determines the target behavior data of the user's binding target hardware, and inputs the target behavior data into the pre-built hardware binding evaluation model to obtain the hardware binding evaluation index. Based on the hardware binding evaluation model, the user's binding process evaluation can be obtained immediately indicators, effectively shortening the evaluation cycle.
[0025]The first embodiment of the present invention relates to a binding process evaluation method, and the specific process is as follows figure 1 shown. The implementation details of the binding process evaluation method in this embodiment will be specifically described below. The following content is only provided for the convenience of understanding, and is not necessary for implementing this solution.
[0026] Step 101: Acquire binding data from each terminal. The binding data includes: behavior data used by each user to bind hardware and hardware information of the bound hardware.
[0027] In one example, the user's behavioral data is obtained from a smartphone, and the behavioral data includes each button click, the browsing time of each page, and the binding result.
[0028] In one example, the hardware information of the bound hardware is obtained from the smartphone, and the hardware information includes a hardware ID, a hardware type, and a firmware version.
[0029] The above binding data can be stored in the database.
[0030] Step 102: Determine, according to the binding data, target behavior data of the target hardware bound by the user.
[0031] In one example, the target hardware corresponding to the hardware information is obtained from the binding data stored in the database, so as to obtain the target behavior data of the hardware to be evaluated. For example, the target hardware whose hardware ID is 3***8 in the hardware information is obtained. Behavior data or obtain target behavior data of target hardware whose hardware class is a specified class.
[0032] Step 103: Input the target behavior data into a pre-built hardware binding evaluation model to obtain a hardware binding evaluation index. The hardware binding evaluation model is used to perform statistics on target behavior data, and the hardware binding evaluation index is used to evaluate the hardware binding process.
[0033] In one example, the hardware binding process is: prepare, connect, result. In the preparation process, the user makes the device in the correct binding state and binding environment, and the step page is p i , which represents step i of the preparation process. In the connection process, the user completes the device connection according to the distribution network guidance, and the network distribution method is one or more of AP distribution network, Bluetooth distribution network, scanning code distribution network, protocol wired network distribution, protocol wireless distribution network, and acoustic wave distribution network. species, the step page is Indicates the jth step of the kth method of the connection process. The help link is provided in the binding step. When the user cannot understand the interface or state, they can click to get help. H i Represents the help page for step i of the preparation process, Represents the help page for step j of method k of the connection process. Binding results with success R 1 , failed R 2 , exit R 3 three.
[0034] In one example, the hardware binding evaluation model is used to: count the number of visits of each page of the hardware binding process within a preset time period; the visit amount is obtained according to the target behavior data within the preset time period; The binding path evaluation index is obtained from the number of visits of each page and a preset mapping relationship, wherein the preset mapping relationship is set according to the page order of the hardware binding process. Specifically, the number of visits to each step page is obtained according to the number of button clicks in the behavior data. The number of button clicks is equal to the number of page views of the page linked by the button. The preset mapping relationship is the preset different binding paths. The fixed path is from the beginning of the binding to the end of the binding, the pages that the user passes through and the sequence of the pages they pass through, you can use the icon form to intuitively represent the path of the user binding, for example, the Sankey diagram, the user binding path analysis Sankey diagram can be Intuitively show the inflow and outflow of hardware binding pages within a preset time period. According to the thickness, you can quickly compare and observe the user's binding execution and binding results in the binding, which is convenient for comparison before and after optimization.
[0035] In one example, the hardware binding evaluation index includes: the help page browsing evaluation index of the binding step; the help page browsing evaluation index is used to prompt whether the step page of the binding step needs to be optimized. For example, obtain the page views of each help page from the target behavior data within a preset time period, and prepare the page views of the help page at step i of the process Help page views for step j of method k of the connection process The number of visits to the preparation page corresponding to the help page and connection page of visits to get the click-through rate of the help page Get the browsing time of the help page for step i of the preparation process from the behavior data Browsing time of the help page of step j of the k-th method of the connection process Taking the browsing time and number of visits of each help page when each user binds the target hardware within the preset time period as a statistical sample, the statistical indicators such as the mean, standard deviation, median, maximum, and minimum values are calculated. Help page browsing evaluation indicators may be the aforementioned statistical indicators, help page click-through rate, average number of help page visits by users, average help page visit time, etc. Specific help page evaluation indicators can be set according to actual business needs. The help page browsing evaluation indicator is used to prompt whether the step page of the binding step needs to be optimized. For example, when the daily average help click rate of a certain page in the selected statistical time period is higher than the preset click rate c, and the average number of users' help visits When it is greater than d times and the average help access time is greater than e seconds, it is concluded that the page in this step needs to be optimized. Among them, c, d, and e are standard values customized according to actual business needs. It is worth mentioning that the standard values and the help page The browsing evaluation index value can be set according to the actual business situation. According to the browsing information of the help page, the click evaluation index of the help page is obtained, which can judge whether the steps corresponding to the help page are easy to understand and operate, so as to accurately evaluate whether the steps of the binding process are easy to understand.
[0036] In an example, the hardware binding evaluation index includes: binding result evaluation index; inputting the binding result in the target behavior data into the hardware binding evaluation model to obtain the hardware binding evaluation index. Binding results include: success R 1 , which fails R 2 , exit R 3; The hardware binding evaluation model is used to: obtain the binding result evaluation index according to the binding result of the preset time period.
[0037] In one example, acquiring the binding result evaluation indicator according to the binding result in the preset time period includes: acquiring the binding failure corresponding to the preset failure cause according to the binding result in the preset time period and the preset failure reason. User volume; the user volume of the logout page and logout page is obtained according to the binding result of the preset time period. For example, according to the statistical analysis of the binding results of the target behavior data within a preset time period, the binding result evaluation index, the total number of bindings U, and the number of successful bindings are obtained. failures Exits Binding success rate: Count the number of users with the i-th failure cause in the preset time period And sort; record the exit page, and count the number of users of each exit page within a preset time period
[0038] In this embodiment, the binding data is obtained from each terminal, and a large number of statistical samples can be obtained. The collected data comes from the terminal, the data is objective and accurate, and no manual data collection is required, which reduces the demand for human resources and time resources for data collection. The binding data determines the target behavior data for the user to bind the target hardware, and inputs the target behavior data into the pre-built hardware binding evaluation model to obtain the hardware binding evaluation index. Based on the hardware binding evaluation model, the user's binding can be obtained immediately. Process evaluation indicators, effectively shorten the evaluation cycle.
[0039] A second embodiment of the present invention relates to a binding process evaluation method. The second embodiment is substantially the same as the first embodiment, and the main difference is that: in the second embodiment of the present invention, the binding data further includes: the user information of each user; the data obtained from each terminal After binding the data, the method further includes: acquiring user behavior data of the hardware bound by the specified user according to the binding data, wherein the specified user is bound to multiple hardwares, and the multiple hardwares include the target hardware; The user behavior data is input into a pre-built user binding evaluation model to obtain a user binding evaluation index; wherein, the user binding evaluation model is used to perform statistics on the user behavior data, and the user binding evaluation index is used to combine all user binding evaluation indicators. The hardware binding index evaluation hardware binding process is described above.
[0040] The second embodiment of the present invention relates to a binding process evaluation method, and the specific process is as follows figure 2 shown:
[0041] Step 201: Acquire binding data from each terminal.
[0042] In one example, the binding data may also include user information of each user. User information such as user ID, region, age, gender, etc.
[0043] Step 202: Determine, according to the binding data, target behavior data of the target hardware bound by the user.
[0044] In one example, the target behavior data also includes the time of each step, the time of each step includes, the time of the preparation step time per connection step total time
[0045] Step 203: Input the target behavior data into a pre-built hardware binding evaluation model to obtain a hardware binding evaluation index.
[0046] In an example, the time of each step in the target behavior data is input into a pre-built hardware binding evaluation model, the binding time of each user within a preset time period is counted as a statistical sample, and the hardware binding time index is calculated, Such as mean, standard deviation, median, maximum, minimum and other statistical indicators.
[0047] Step 204: Acquire user behavior data of the hardware bound by the specified user according to the binding data. Wherein, the designated user is bound to multiple pieces of hardware, and the multiple pieces of hardware include the target hardware.
[0048] In one example, the binding data also includes: environmental information, such as terminal system, terminal type, application version, network information, etc. For the account ID of the specified user, the user is bound to different intelligent hardware by collecting and obtaining the specified environmental information. user behavior data, such as binding time, help clicks, and binding results. The binding time of the user behavior data, that is, the time used for the preparation steps to specify the user's initial binding of different hardware time per connection step Specifies the total time for user binding Help clicks i.e. page views per help page time per help page The binding result is the result of specifying the user to bind different hardware for the first time: successful R 1 , which fails R 2 , exit R 3.
[0049] Step 205: Input the user behavior data into a pre-built user binding evaluation model to obtain a user binding evaluation index.
[0050] In one example, the above-mentioned user behavior data is input into a pre-built user binding evaluation model to obtain user binding evaluation indicators, that is, the user binding time index, the user help click index, and the user binding result index. The user binding time indicator takes the binding time of the specified user bound to other hardware within a preset time period as a statistical sample, and obtains statistical indicators such as the mean, standard deviation, median, maximum, and minimum values. User help click on the indicator, take the help browsing time of a specified user bound to other hardware within a preset time period as a statistical sample, and obtain statistical indicators such as the mean, standard deviation, median, maximum, and minimum values. Binding result evaluation index, that is, obtain the result of the specified user's initial binding of different hardware, if it fails, record and return the failure reason, and if it exits, record the exit page.
[0051]In an example, after obtaining the user binding evaluation index and the hardware binding evaluation index, the hardware binding step time index of the step page is obtained from the hardware binding evaluation index; The user binding step time usage indicator on the step page; according to the hardware binding step time usage indicator and the user binding step time usage indicator, it is prompted whether there is room for optimization on the step page. For example, compare the time indicators of the hardware binding steps first, and then compare the time indicators of the user binding steps when the hardware binding step time indicators in the preset time period are higher than the preset optimization value of a second, and select multiple bindings. Users of the hardware to be evaluated and other similar hardware are compared horizontally. When the user binding time index of the user bound to the target hardware is higher than the sum of the average and standard deviation of other hardware indexes by b seconds, the result is obtained. Metrics can be optimized. Where a and b are custom standard values.
[0052] In one example, the smart hardware binding process conditions are evaluated, such as figure 1 As shown, the intelligent hardware binding process evaluation is obtained according to the single hardware evaluation and the single user evaluation, the execution steps of the single hardware evaluation are steps 201 to 203, and the single hardware evaluation includes: binding execution evaluation and binding result evaluation. The binding execution evaluation is based on the binding time, which helps to click on the evaluation. The binding execution evaluation is to realize the evaluation of the intelligent hardware binding execution status. The binding time is input into the hardware binding evaluation model to obtain the hardware binding step time index, which will help Click to enter the hardware binding evaluation model to get the help page to browse the evaluation indicators, and then carry out the evaluation. The binding result evaluation is to obtain the binding result of the target behavior data, input the binding result of the target behavior data into the hardware binding evaluation model to obtain the binding result evaluation index, and use the binding result evaluation index to complete the hardware binding. situation is assessed. The user binding path is to input the click of each button in the target behavior data into the hardware binding evaluation model to obtain the binding path evaluation index, and then perform evaluation. On the basis of the single hardware evaluation, the evaluation is carried out according to a single user. The steps of the single user binding evaluation are 204 to 205. Use the binding time of the user behavior data, help click, exit the analysis, and enter the user binding evaluation model to obtain the user binding. Evaluation Metrics. The single-hardware binding evaluation and the single-user binding evaluation are combined to obtain the hardware binding evaluation.
[0053] In this example, a smart speaker with a hardware ID of 3***8 is used as an example. The terminal collects the binding data in the user binding process in November 2019, preprocesses the original data, and deletes suspicious and incorrect data. Each evaluation index is obtained according to the binding evaluation model.
[0054] For the single-hardware binding evaluation of a speaker connected to the AP network, the binding time from each step, such as binding preparation, connecting to Wi-Fi, switching hotspots, and connecting waiting; help clicks, such as the number of clicks on the binding preparation help page and Evaluate from the perspectives of each browsing time, binding results, etc. Table 1 shows the statistics of some iOS user indicators of a speaker in November 2019. Among them, in the binding result column, the result is 0, which means the binding fails, the result is 1, the binding is successful, and the result is empty, which means exit the binding The empty data means that no data has been obtained, the binding execution page data being empty means that the user has not viewed the page, and the previous step of the empty data is the user exit page.
[0055] Table 1
[0056]
[0057] Input the data into the pre-built hardware binding evaluation model to obtain the hardware binding evaluation index, as shown in Table 2.
[0058] Table 2
[0059]
[0060] The binding results evaluation indicators are shown in Table 3.
[0061] table 3
[0062]
[0063] In the binding results, the statistical ranking of the reasons for binding failures is shown in Table 4.
[0064] Table 4
[0065]
[0066] Draw a Sankey diagram of the audio's bound hardware path based on the acquired hardware behavior data.
[0067] Obtain the user behavior data of the hardware bound by the specified user according to the binding data. In this embodiment, the binding evaluation of multiple users bound to a certain speaker and other hardware with the same network distribution method is performed, including the binding of each step. When it is fixed, it means binding preparation, connecting to Wi-Fi, switching hotspots, and waiting for connection; help click means the number of clicks on the binding preparation help page and the duration of each browsing of the help page; binding results. User behavior data of a user in Table 5, the second row 3***8 is the target hardware.
[0068] table 5
[0069]
[0070] Binding implementation evaluation of speakers 3***8. Based on the statistics and calculation results of the indicators of the intelligent hardware binding process evaluation model, the hardware binding step time index of a speaker, that is, the average duration of the binding preparation page is 15.23 seconds, which is 10 seconds higher than the default value, and the help page browsing evaluation index is daily The average help click rate is 76%, the average number of help visits is 1.02, and the average help visit time is 4.72 seconds, which is higher than the standard value. Furthermore, in the single-user binding evaluation, the user binding steps of a certain user, such as the binding preparation page, took 15.17 seconds, which was higher than the sum of the average and standard deviation of other hardware indicators at 6.38 seconds. It is concluded that there is room for optimization in the binding preparation steps page of a certain speaker. It is speculated that there may be difficulties in user understanding, and it is recommended to optimize the display of graphic and text information on the page.
[0071] Binding result evaluation, based on the intelligent hardware binding process status evaluation model index statistics and the binding result evaluation index obtained from the calculation results, the daily average binding success rate of a speaker is 84.34%, and there is a certain room for improvement. Among the reasons for the failure of binding, F4_ manual switching failed, please re-bind, which is related to the interface operation and is caused by user cancellation. It is recommended to optimize the page button layout, reduce the user's cancellation of manual switching behavior, reduce the failure count, and improve the success rate.
[0072] Binding path evaluation, draw a Sankey diagram according to the user binding path evaluation index, and analyze the user binding path. The Sankey diagram intuitively shows the inflow and outflow of hardware binding pages within the statistical time. According to the thickness, you can quickly compare and observe the user's binding process. Binding execution and binding results are easy to compare before and after optimization.
[0073] In this embodiment, the user binding evaluation model and the indicators obtained by the hardware binding target evaluation model are combined to evaluate the hardware binding process, which not only excludes the influence of the user's operating habits, but also can bind other hardware bound by the user. Compared with the target hardware binding data, the evaluation of the target hardware binding process is more accurate and comprehensive.
[0074] The steps of the above various methods are divided only for the purpose of describing clearly. During implementation, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as the same logical relationship is included, they are all within the protection scope of this patent. ;Adding insignificant modifications to the algorithm or process or introducing insignificant designs, but not changing the core design of the algorithm and process are all within the scope of protection of this patent.
[0075] The third embodiment of the present invention relates to a binding process evaluation device, such as Figure 4 As shown, it includes: a binding data obtaining device 401, configured to obtain binding data obtained from a terminal, wherein the binding data includes: behavior data used by each user to bind hardware and hardware information of the bound hardware; The target behavior data acquisition device 402 is used to determine the target behavior data of the user to bind the target hardware according to the binding; the evaluation index acquisition device 403 is used to input the target behavior data into a pre-built hardware binding evaluation model to obtain the hardware A binding evaluation index, wherein the hardware binding evaluation model is used to perform statistics on target behavior data, and the hardware binding evaluation index is used to evaluate the hardware binding process.
[0076] In one example, the evaluation indicator obtaining means 403 is further configured to count the visits of each page of the hardware binding process within a preset time period; the visits are obtained according to the target behavior data within the preset time period; according to the The binding path evaluation index is obtained from the number of visits of each page and a preset mapping relationship, wherein the preset mapping relationship is set according to the page order of the hardware binding process.
[0077] In one example, the evaluation index obtaining means 403 is further configured to obtain the help page browsing evaluation index of the binding step, and the help page browsing evaluation index is used to prompt whether the step page of the binding step needs to be optimized.
[0078] In one example, the evaluation index obtaining means 403 is further configured to input the binding result in the target behavior data into the hardware binding evaluation model to obtain the hardware binding evaluation index; wherein the binding result includes: success, If it fails, exit; the hardware binding evaluation model is used for: obtaining the binding result evaluation index according to the binding result in the preset time period.
[0079] In one example, the evaluation indicator obtaining means 403 is further configured to obtain the number of users whose binding fails corresponding to the preset failure cause according to the binding result and the preset failure reason in the preset time period; Get the exit page and the number of users who exit the page based on the result.
[0080] In one example, the evaluation index obtaining means 403 is further configured to obtain user behavior data of hardware bound by a specified user according to the binding data, wherein the specified user is bound to a plurality of hardware, and the plurality of hardware includes all hardware. the target hardware; input the user behavior data into a pre-built user binding evaluation model to obtain user binding evaluation indicators; wherein the user binding evaluation model is used to perform statistics on user behavior data, and the user binding evaluation The index is used to evaluate the hardware binding process in combination with the hardware binding index.
[0081] In one example, the evaluation index obtaining means 403 is further configured to prompt whether there is room for optimization on the step page according to the hardware binding step time index and the user binding step time index.
[0082] It is not difficult to find that this embodiment is a system example corresponding to the first embodiment, and this embodiment can be implemented in cooperation with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and are not repeated here in order to reduce repetition. Correspondingly, the related technical details mentioned in this embodiment can also be applied to the first embodiment.
[0083] It is worth mentioning that each module involved in this embodiment is a logical module. In practical applications, a logical unit may be a physical unit, a part of a physical unit, or multiple physical units. A composite implementation of the unit. In addition, in order to highlight the innovative part of the present invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other units in this embodiment.
[0084] The fourth embodiment of the present invention relates to a server, such as Figure 5 As shown, at least one processor 501 is included; and a memory 502 is communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor At least one processor executes to enable the at least one processor to execute the above-described binding process evaluation method.
[0085]The memory and the processor are connected by a bus, and the bus may include any number of interconnected buses and bridges, and the bus connects one or more processors and various circuits of the memory. The bus may also connect together various other circuits, such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides the interface between the bus and the transceiver. A transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing a means for communicating with various other devices over a transmission medium. The data processed by the processor is transmitted on the wireless medium through the antenna, and further, the antenna also receives the data and transmits the data to the processor.
[0086] The processor manages the bus and general processing, and can also provide various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. Instead, memory may be used to store data used by the processor in performing operations.
[0087] A fifth embodiment of the present invention relates to a computer-readable storage medium storing a computer program. The above method embodiments are implemented when the computer program is executed by the processor.
[0088] That is, those skilled in the art can understand that all or part of the steps in the method of implementing the above embodiments can be completed by instructing relevant hardware through a program, and the program is stored in a storage medium and includes several instructions to make a device ( It may be a single chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes.
[0089] Those of ordinary skill in the art can understand that the above-mentioned embodiments are specific examples for realizing the present invention, and in practical applications, various changes in form and details can be made without departing from the spirit and the spirit of the present invention. scope.
