Method and apparatus for discovering pages with need for help service deployment

Abstract

The embodiment of the present specification provides a method and device for discovering a page with a help service deployment requirement. In the method, page access data is acquired, the page access data including data in at least one dimension of business, user and page; a page to be evaluated is determined according to the page access data; for each page to be evaluated, a help rate of the page to be evaluated is calculated according to historical help data corresponding to a help channel deployed by the page to be evaluated; and a page to be deployed with a help service is determined according to the help rate of each page to be evaluated, the help service being used to solve a help initiated by a user.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and more specifically, to a method and apparatus for discovering pages that require the deployment of help services. Background Technology

[0002] As the internet continues to develop and mature, corresponding internet products have emerged and are widely used. Users inevitably encounter various problems while using these products, such as not being able to find the entry point to a certain application module or experiencing system crashes. When users encounter problems, they need to contact the relevant product or operations team for resolution; otherwise, the user experience will be severely impacted.

[0003] As user experience becomes increasingly important, a common practice is to deploy help channels within products to ensure users can provide timely feedback on issues encountered during product use. When users encounter problems while using the product, they can use these help channels to report the issues. Summary of the Invention

[0004] In view of the above, embodiments of this specification provide a method and apparatus for discovering pages that require the deployment of help-seeking services. Through the technical solutions provided by these embodiments, pages requiring the deployment of help-seeking services can be discovered in real time, enabling these pages to deploy help-seeking services promptly before impacting user experience, thereby resolving user-initiated requests for assistance.

[0005] According to one aspect of the embodiments of this specification, a method for discovering pages with a need for deploying help services is provided, comprising: acquiring page access data, the page access data including data from at least one of three dimensions: business, user, and page; determining pages to be evaluated based on the page access data; calculating the help rate of each page to be evaluated based on historical help data corresponding to the help channels deployed on the page to be evaluated; and determining pages to be deployed with help services based on the help rates of each page to be evaluated, the help services being used to resolve user-initiated help requests.

[0006] According to another aspect of the embodiments of this specification, a data acquisition unit is also provided to acquire page access data, the page access data including data of at least one of three dimensions: business, user, and page; a first page determination unit to determine pages to be evaluated based on the page access data; a help rate calculation unit to calculate the help rate of each page to be evaluated based on historical help data corresponding to the help channels deployed on the page to be evaluated; and a second page determination unit to determine pages to deploy help services based on the help rates of each page to be evaluated, the help services being used to resolve user-initiated help requests.

[0007] According to another aspect of the embodiments of this specification, an electronic device is also provided, comprising: at least one processor, a memory coupled to the at least one processor, and a computer program stored on the memory, wherein the at least one processor executes the computer program to implement the method for discovering a page with a need for help service deployment as described above.

[0008] According to another aspect of the embodiments of this specification, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the method described above for discovering pages with a need for help service deployment.

[0009] According to another aspect of the embodiments of this specification, a computer program product is also provided, including a computer program that, when executed by a processor, implements the method for discovering pages with a need for help service deployment as described above. Attached Figure Description

[0010] A further understanding of the nature and advantages of the embodiments described in this specification can be achieved by referring to the following accompanying drawings. In the drawings, similar components or features may have the same reference numerals.

[0011] Figure 1 A flowchart illustrating an example of a method for discovering pages with a need for help service deployment, according to an embodiment of this specification.

[0012] Figure 2 A flowchart illustrating an example of determining a page to be evaluated based on user dimension data according to an embodiment of this specification is shown.

[0013] Figure 3 A flowchart illustrating another example of determining a page to be evaluated based on user dimension data according to an embodiment of this specification is shown.

[0014] Figure 4 A flowchart illustrating an example of determining a page to be evaluated based on business dimension data according to an embodiment of this specification is shown.

[0015] Figure 5 A flowchart is shown for another example 500 of determining a page to be evaluated based on page access data according to an embodiment of this specification.

[0016] Figure 6 A block diagram illustrating an example of an apparatus for discovering pages with a need for help service deployment, according to an embodiment of this specification.

[0017] Figure 7 A block diagram of an electronic device for implementing a page discovery method according to an embodiment of this specification is shown. Detailed Implementation

[0018] The subject matter described herein will be discussed below with reference to exemplary embodiments. It should be understood that these embodiments are discussed merely to enable those skilled in the art to better understand and implement the subject matter described herein, and are not intended to limit the scope, applicability, or examples set forth in the claims. The function and arrangement of the elements discussed may be changed without departing from the scope of the embodiments described herein. Various processes or components may be omitted, substituted, or added as needed in the various examples. Furthermore, features described in some examples may be combined in other examples.

[0019] As used herein, the term "comprising" and its variations are open terms meaning "including but not limited to". The term "based on" means "at least partially based on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other definitions, whether explicit or implicit, may be included below. Unless explicitly indicated by the context, the definition of a term shall remain consistent throughout the specification.

[0020] As the internet continues to develop and mature, corresponding internet products have emerged and are widely used. Users inevitably encounter various problems while using these products, such as not being able to find the entry point to a certain application module or experiencing system crashes. When users encounter problems, they need to contact the relevant product or operations team for resolution; otherwise, the user experience will be severely impacted.

[0021] As user experience becomes increasingly important, a common practice is to deploy help channels within products to ensure users can provide timely feedback on issues encountered during product use. When users encounter problems while using the product, they can use these help channels to report the issues.

[0022] However, help channels can only provide users with feedback on problems, but cannot solve the problems raised by users. As a result, the problems that users ask for help cannot be resolved in a timely manner, which will also lead to a poor user experience and even cause users to abandon the Internet product.

[0023] In view of the above, embodiments of this specification provide a method and apparatus for discovering pages requiring the deployment of help-seeking services. In this method, page access data is acquired, including data from at least one of three dimensions: business, user, and page. Pages to be evaluated are determined based on the page access data. For each page to be evaluated, a help-seeking rate is calculated based on historical help-seeking data corresponding to the help-seeking channels deployed on that page. Finally, pages requiring the deployment of help-seeking services are determined based on the help-seeking rates of each page to be evaluated. These help-seeking services are used to resolve user requests. The technical solution provided by these embodiments enables the real-time discovery of pages requiring the deployment of help-seeking services, allowing these pages to deploy help-seeking services promptly before impacting user experience, thus resolving user-initiated requests.

[0024] The method and apparatus for discovering pages that require help-seeking service deployment, as provided in the embodiments of this specification, will now be described with reference to the accompanying drawings.

[0025] Figure 1 A flowchart of an example 100 of a method for discovering pages with a need for help service deployment, according to an embodiment of this specification, is shown.

[0026] like Figure 1 As shown, page access data can be obtained at 110.

[0027] Page access data includes historical data related to pages visited by users, and can include data from at least one of the three dimensions: business, user, and page.

[0028] Page-level data (hereinafter referred to as page-level data) can include visited pages. In one example, visited pages can be filtered conditionally, and the filtering conditions can be customized. For example, specific pages can be filtered, so the page-level data can include the specific pages that have been visited.

[0029] User-centric data (hereinafter referred to as user-dimensional data) can include the pages visited by each user, the time of page visits, and the requests for help initiated by each user on the page. In user-dimensional data, pages and requests for help can be stored together, and each request for help can be associated with the page that initiated it, so that each request for help initiated on a page can be identified through a single page.

[0030] Business-dimensional data (hereinafter referred to as business dimension data) can include multiple sets of business dimension data categorized according to various business types. Each business type's corresponding business dimension data can include product information, page information, and user information related to that business. User information related to that business can include user dimension data, such as pages visited by users and requests for help initiated on those pages. The user dimension data included in the business dimension data can be categorized by user. In one example, the business dimension data can be conditionally filtered. The filtering conditions can be customized; for example, data from a specific business can be filtered. Therefore, the obtained business dimension data will include business dimension data corresponding to the specified business, while business dimension data from other businesses will not be included.

[0031] In one example, page access data can be obtained from a page access backend data system. This system can store data related to each user's page access via a terminal device, as well as the storage time of each data entry. In this example, the page access data directly obtained from the page access backend data system can be used as the page access data obtained in this embodiment, or the obtained page access data can be filtered after being retrieved from the system, and the filtered data can then be used as the page access data obtained in this embodiment.

[0032] In one example, page access data within a specified range can be retrieved. This range can include at least one of a specified time period, a specified business scope, and a specified page scope. When retrieving page access data within a specified time period, all retrieved page access data belongs to data generated within that specified time period. When retrieving page access data within a specified business scope, the retrieved page access data includes business dimension data for that specified business. When retrieving page access data within a specified page scope, the retrieved page access data includes the specified pages.

[0033] In one example, page view data can be retrieved using an electronic form. In this example, the electronic form can interface with the page view backend data system, allowing it to directly obtain page view data from the system. Furthermore, the electronic form can be configured with data filtering conditions, which can be customized. For example, data filtering conditions can include at least one of the following: specified business function, specified page, specified time period, etc.

[0034] In this example, electronic forms facilitate the automatic retrieval of page access data from the page access backend data system. Furthermore, the data filtering conditions of the electronic forms can filter out page access data that meets custom criteria, thereby enabling more accurate discovery of pages for which help services need to be deployed using page access data with custom criteria.

[0035] In step 120, the page to be evaluated can be determined based on page access data.

[0036] In the embodiments of this specification, different dimensions of page access data can be used to determine the pages to be evaluated in different ways. The determined pages to be evaluated can be used to further filter the pages to be deployed with help services based on the pages' help request rate; that is, the pages to be deployed with help services are a subset of the pages to be evaluated.

[0037] In one example, when page visit data includes page dimension data, each page included in the page dimension data can be identified as the page to be evaluated. In another example, when page visit data includes page dimension data, a specific page from the pages included in the page dimension data can be identified as the page to be evaluated.

[0038] Figure 2 A flowchart illustrating an example 200 of determining a page to be evaluated based on user dimension data according to an embodiment of this specification is shown.

[0039] like Figure 2 As shown in 1211, when the page access data includes user dimension data, the user seeking help can be identified based on the help requests initiated by the user in the user dimension data.

[0040] In this example, user-dimensional data can include the pages visited by the user and the requests for help initiated by the user. This allows for filtering of user-initiated requests for help from the user-dimensional data. Each request for help can be associated with the user who initiated it, and also with the page the user visited when the request was initiated. Therefore, the user who initiated each request for help can be identified based on the requests.

[0041] In one example, the user corresponding to each of the filtered requests can be identified.

[0042] In another example, a subset of requests for help can be filtered from user-initiated requests, and then the users who initiated those requests can be identified as the users seeking help.

[0043] One filtering method involves filtering based on the number of requests for help. Specifically, user-initiated requests for help can include multiple types. The requests in the user-dimensional data can be categorized by type, and the number of requests for each type can be determined. Then, requests for the type with the highest number of requests can be filtered out. In one example, the various request types can be sorted according to the number of requests for each type to obtain a request type sequence. Then, requests for the type corresponding to the highest number of requests can be filtered out in descending order.

[0044] In the example above, by filtering out a large number of requests for help, the amount of data processing can be reduced while ensuring that users' concentrated requests for help have a higher probability of being deployed on the corresponding pages.

[0045] In 1213, the pages to be evaluated are determined based on the user dimension data, including the pages visited by users seeking help.

[0046] In one example, all pages visited by the user seeking help in the user dimension data can be identified as pages to be evaluated.

[0047] In another example, the page to be evaluated can be filtered from the pages visited by the user seeking help, which are included in the user dimension data, based on at least one of the following filtering conditions: specified business, specified page, and specified page access duration threshold.

[0048] When the filtering criteria include a specific business, pages related to that specific business can be filtered from the user dimension data (pages visited by users seeking help) as pages to be evaluated. Thus, all filtered pages to be evaluated are related to the specified business. In this example, pages related to the specified business may include pages with business attributes corresponding to that specific business.

[0049] When the filtering criteria include a specified page, the specified page in the user dimension data that the user who requested help visited can be identified as the page to be evaluated.

[0050] In this example, the acquired page visit data may also include the visit duration for each page. When the filtering criteria include a specified page visit duration threshold, pages in the user dimension data whose visit duration exceeds the specified page visit duration threshold can be identified as pages to be evaluated.

[0051] In this example, pages with short access durations can be considered invalid access pages, such as pages accessed by mistake. For invalid access pages, users may not have browsed them carefully or even browsed them at all. Therefore, by setting a page access duration threshold, invalid access pages with short access durations can be filtered out, thereby improving the quality of the pages being evaluated.

[0052] In this example, when there are multiple filter conditions, each filter condition can be used to filter the pages visited by the user seeking help, which are included in the user dimension data. Then, the pages to be evaluated corresponding to each filter condition can be merged to determine the pages to be evaluated.

[0053] Figure 3 A flowchart is shown for another example 300 of determining a page to be evaluated based on user dimension data according to an embodiment of this specification.

[0054] like Figure 3 As shown in 1221, when the page access data includes business dimension data, users related to a specified business can be identified based on this business dimension data.

[0055] Business dimension data for each business can include: each user related to the business and the corresponding user dimension data, each user's operation information for the business, and the pages with business attributes corresponding to the business.

[0056] Users related to the business can include those who have consulted about the business, those who have used the business, and those who have logged into the corresponding pages. The user dimension data for each user in the business dimension data includes the pages visited by that user. In one example, the pages visited by each user in the business dimension data may include only the business-related pages visited by that user. In another example, the pages visited by each user in the business dimension data may include both business-related and business-unrelated pages visited by that user.

[0057] Operation information can include various operation types such as clicks and swipes, questions for help, input information, access time, and access duration. Pages with business attributes are those that can display business attributes and allow related business operations to be performed on the page.

[0058] In 1223, the pages to be evaluated can be determined based on the identified users in the business dimension data.

[0059] In one example, the pages visited by each identified user are filtered from the business dimension data, and these filtered pages are designated as the pages to be evaluated. In one example, the pages visited by each user filtered from the business dimension data can include pages related to the corresponding business visited by each user. In another example, the pages visited by each user filtered from the business dimension data can include both pages related to the corresponding business visited by each user and pages unrelated to the corresponding business visited by each user.

[0060] In one example, after identifying users relevant to a specific business, requests for help initiated by these users can be filtered within the business dimension data. Then, these requests can be further filtered to include the top-ranked requests by number. The users requesting help are then identified based on this further filtering. Next, the pages to be evaluated are determined based on the pages visited by these users, as included in the business dimension data. The steps in this example can be referenced... Figure 2 Instructions for operation shown in the example.

[0061] Figure 4 A flowchart of an example 400 for determining a page to be evaluated based on business dimension data according to an embodiment of this specification is shown.

[0062] like Figure 4 As shown in 1231, when the page access data includes business dimension data, the business page with business attributes corresponding to the specified business can be determined based on the business dimension data.

[0063] In one example, when the business dimension data only includes business dimension data for a specific business, all pages corresponding to all businesses in the business dimension data can be identified as the business pages corresponding to the specified business. In another example, when the business dimension data includes business dimension data for both the specified and non-specified businesses, the business pages corresponding to the specified business can be filtered out from the business dimension data.

[0064] In 1233, the page to be evaluated can be determined based on the identified business page.

[0065] In one example, all identified business pages can be designated as pages to be evaluated.

[0066] In another example, a subset of the identified business pages can be selected as the pages to be evaluated. In one example, requests for help initiated on the identified business pages can be detected in the business dimension data. These requests can be aggregated and filtered to identify the top-ranked requests by number, and the users who initiated these filtered requests can be identified as request-seeking users. Then, the pages to be evaluated can be determined based on the pages visited by these request-seeking users included in the business dimension data. The operations in this example can be referenced... Figure 2 Instructions for operation shown in the example.

[0067] Figure 5 A flowchart illustrating another example of determining a page to be evaluated based on user dimension data in page access data, according to an embodiment of this specification.

[0068] like Figure 5 As shown in 1241, when the page access data includes user-dimensional data and / or business-dimensional data, the requests for help initiated by users can be filtered out from the page access data, with the second-highest number of requests ranking first.

[0069] In one example, all user-initiated requests for help can be extracted from page access data. These requests are then categorized by type to determine the number of requests included in each type. Next, each request type is sorted according to the number of requests it includes, resulting in a request type sequence. The request that appears second to third in the sequence is then selected.

[0070] In step 1243, for each selected request for help, the page that appears most frequently in the page access data is determined to be the third specified page.

[0071] For each selected request for help, the page access data is filtered to identify the page where the request was initiated. Each request can correspond to a set of pages, and this set of pages includes the third specified number of pages that initiated the request the most. For example, if the third specified number is the first 5 pages, then the third specified number is 5, and thus the set of pages corresponding to each request includes the 5 pages that initiated the request the most.

[0072] At step 1245, the selected requests for help are cross-referenced with the corresponding pages to determine the page containing the requests for help.

[0073] Each request for help can be grouped into a set of pages, and each page group can include at least one page. A single page can have multiple requests for help initiated, and thus that page can appear in multiple page groups corresponding to those requests.

[0074] By cross-referencing the page groups corresponding to each request for help, the requests initiated on each page can be identified. Pages with a relatively large number of requests can then be designated as the central request page. In one method of determining the central request page, the pages can be sorted based on the number of requests initiated on each page, and the pages with the most requests ranked first can be designated as the central request page.

[0075] In 1247, the help request page was identified as a page to be evaluated.

[0076] Back Figure 1 After identifying the pages to be evaluated, at step 130, for each page to be evaluated, the help rate of that page is calculated based on the historical help data corresponding to the various help channels deployed on that page.

[0077] In the embodiments of this specification, the help channels are methods for providing users with feedback on problems. The help channels deployed on a page may include: self-service help, IVR voice help, hotline human help, and online human help, etc. Different pages may deploy different help channels. When a user encounters a problem requiring assistance while visiting a page, the user can customize and select a help channel to seek help. Therefore, the number of help requests corresponding to different help channels deployed on the same page may be different.

[0078] In the embodiments of this specification, the historical help data corresponding to each help channel may include at least one of the following: the number of users who used the help channel to seek help and the total number of users, the time each user used the help channel, and the question asked. In one example, the historical help data for each help channel may come from the acquired page access data. In another example, the historical help data for each help channel may be re-acquired based on the data range of the acquired page access data, and the data range may include the time period to which the data belongs.

[0079] The help-seeking rate for a page can represent the proportion of times a help-seeking request occurs on that page. In one example, the help-seeking rate could be the proportion of times a help-seeking request was made. In another example, the help-seeking rate could be the proportion of users who initiated a help-seeking request.

[0080] In one example, for each page to be evaluated, the single-channel help rate of each help channel on the page to be evaluated can be calculated based on the historical help data of each help channel deployed on that page.

[0081] When the help request rate is the proportion of the number of help requests, for each help request channel deployed on each page to be evaluated, the number of times users used that channel to request help can be counted from the historical help request data corresponding to that channel. Additionally, the number of times the evaluation page was accessed can be counted from the historical access data corresponding to that evaluation page. Then, the percentage obtained by dividing the number of help requests by the number of accesses is determined as the single-channel help request rate for that help request channel on that page to be evaluated.

[0082] When the help-seeking rate is the proportion of users who initiate help requests, for each help-seeking channel deployed on each page to be evaluated, the number of users who used that channel to seek help can be counted from the historical help-seeking data corresponding to that channel. Additionally, the number of users who visited the page to be evaluated can be counted from the historical access data corresponding to that page. Then, the percentage obtained by dividing the number of users seeking help by the number of users visiting the page can be determined as the single-channel help-seeking rate for that help-seeking channel on that page to be evaluated.

[0083] For each page to be evaluated, after calculating the single-channel help rate corresponding to each help channel deployed on the page to be evaluated, the help rate of the page to be evaluated can be calculated based on the single-channel help rate of each help channel.

[0084] In one example, the individual help rates of each help channel can be summed, and the sum of the individual help rates can be used as the help rate of the page to be evaluated.

[0085] In another example, the help rate of the page to be evaluated can be calculated based on the single-channel help rate of each help channel and the help cost coefficient and / or help attenuation coefficient corresponding to each help channel.

[0086] In this example, the help-seeking cost coefficient represents the cost of a help-seeking channel. The higher the cost of a help-seeking channel, the larger the corresponding help-seeking cost coefficient; the lower the cost of a help-seeking channel, the smaller the corresponding help-seeking cost coefficient. For example, the self-service help-seeking channel on the page only requires the user to click on the page to seek help. The hotline human assistance channel requires the user to dial the help number provided on the page to seek help from a human. It is clear that the help-seeking cost of the hotline human assistance channel is significantly higher than that of the self-service help-seeking channel. Therefore, the help-seeking cost coefficient of the hotline human assistance channel is higher than that of the self-service help-seeking channel.

[0087] The cost coefficient of a help-seeking channel can reflect the level of a user's need for help and their tendency to resolve the problem. A higher cost coefficient indicates a stronger need for help and a greater tendency to resolve the issue. Conversely, a lower cost coefficient indicates a weaker need for help and a lower tendency to resolve the issue.

[0088] The request-to-response attenuation coefficient can be used to mitigate abnormal increases in requests, balancing the impact of such increases on the request-to-response rate. The more abnormal the increase in requests, the larger the corresponding attenuation coefficient; conversely, the less abnormal the increase, the smaller the coefficient. For example, if a temporary event leads to increased page views and consequently more requests, resulting in abnormal request growth, an attenuation system can be implemented to reduce this abnormal increase.

[0089] In one example, the help request attenuation factor can be set to a value between 0 and 1. For help requests under normal circumstances, the corresponding help request attenuation factor can be set to 1.

[0090] One method for determining the request-for-help attenuation coefficient involves counting the number of page views on the first page under normal conditions and the number of page views on the second page under conditions of abnormal increase in requests for help. The time period for counting the first and second page views is the same, which can be determined by the duration of the abnormal increase in requests for help. For example, if the time period is one day, then the number of page views on the first page under normal conditions and the number of page views on the second page under conditions of abnormal increase in requests for help are counted.

[0091] In the embodiments of this specification, both the help-seeking cost coefficient and the help-seeking attenuation coefficient can be used as weights for the help-seeking channels. For each help-seeking channel, the single-channel help-seeking rate can be multiplied by the help-seeking cost coefficient and / or help-seeking attenuation coefficient corresponding to that help-seeking channel, which are used as weights, to obtain the corrected single-channel help-seeking rate. Then, the corrected single-channel help-seeking rates corresponding to each help-seeking channel can be summed to obtain the help-seeking rate of the corresponding page to be evaluated.

[0092] In step 140, the pages to be deployed for help services are determined based on the help rate of each page to be evaluated.

[0093] In the embodiments of this specification, the help-seeking service can be used to resolve user-submitted questions. In one example, the help-seeking service can be embedded in a page as a service module. After being triggered by the user seeking help, the service module can redirect to a customer service portal where customer service can resolve the user's question. In another example, the help-seeking service includes a knowledge-based Q&A section. After the help-seeking service is embedded in the page, when it is triggered, the service matches the corresponding answer from the knowledge-based Q&A section based on the user's question and provides the matched answer back to the user to resolve their problem.

[0094] In the embodiments of this specification, a specified number of pages with the highest help-seeking rate can be identified as the pages for which the help-seeking service is to be deployed. In one example, the pages to be evaluated can be sorted according to their help-seeking rate to obtain a sequence of pages to be evaluated. This sequence can be arranged in descending order of help-seeking rate or in ascending order of help-seeking rate. Then, the pages with the highest help-seeking rate at the first specified position in the sequence are identified as the pages for which the help-seeking service is to be deployed.

[0095] After identifying the pages for which the help-seeking service needs to be deployed, the identified pages can be output to downstream technical personnel so that they can deploy the help-seeking service on each output page.

[0096] The technical solution provided in this embodiment can identify pages that need to deploy help services in real time, so that these pages can deploy help services in a timely manner before affecting user experience, in order to resolve user-initiated requests for help.

[0097] Figure 6 A block diagram of an example of an apparatus (hereinafter referred to as page discovery apparatus 600) for discovering pages that require the deployment of help services, according to an embodiment of this specification, is shown.

[0098] like Figure 6 As shown, the page discovery device 600 includes: a data acquisition unit 610, a first page determination unit 620, a help rate calculation unit 630, and a second page determination unit 640.

[0099] The data acquisition unit 610 is configured to acquire page access data, which includes data from at least one of the three dimensions: business, user, and page.

[0100] In one example, the data acquisition unit 610 can also be configured to acquire page access data in the form of an electronic form, wherein the electronic form is connected to the page access backend data system and is configured with data filtering conditions.

[0101] The first page determination unit 620 is configured to determine the page to be evaluated based on page access data.

[0102] In one example, the first page determination unit 620 can also be configured to: determine the user seeking help based on the help requests initiated by the user in the user dimension data when the page access data includes user dimension data; and determine the page to be evaluated based on the pages accessed by the user seeking help in the user dimension data.

[0103] In one example, the first page determination unit 620 can also be configured to: filter out the requests for help that are ranked first in terms of quantity from user-dimensional data, including requests for help initiated by users; and determine the user who initiated the filtered requests for help as the requesting user.

[0104] In one example, the first page determination unit 620 can also be configured to: filter out the pages to be evaluated from the pages visited by the user seeking help, which are included in the user dimension data, based on at least one of the following filtering conditions: specified business, specified page, and specified page access duration threshold.

[0105] In one example, the first page determination unit 620 can also be configured to: determine users related to a specified business based on the business dimension data when the page access data includes business dimension data; and determine the page to be evaluated based on the determined users in the business dimension data.

[0106] In one example, the first page determination unit 620 can also be configured to: determine the business page with business attributes corresponding to a specified business based on the business dimension data when the page access data includes business dimension data; and determine the page to be evaluated based on the determined business page.

[0107] In one example, the first page determination unit 620 can also be configured to: when the page access data includes user-dimensional data and / or business-dimensional data, filter out the requests initiated by users that rank second-to-last in terms of frequency from the page access data; for each of the filtered requests, determine the page that ranks third-to-last in terms of the frequency of the request from the page access data; cross-compare the determined pages corresponding to each of the filtered requests to determine the pages in the request set; and determine the pages in the request set as the pages to be evaluated.

[0108] The help request rate calculation unit 630 is configured to calculate the help request rate of each page to be evaluated based on the historical help request data corresponding to the help request channels deployed on that page.

[0109] In one example, the help request rate calculation unit 630 can also be configured to: calculate the single-channel help request rate of each help request channel on the page to be evaluated based on the historical help request data of each help request channel deployed on the page to be evaluated; and calculate the help request rate of the page to be evaluated based on the single-channel help request rate of each help request channel.

[0110] In one example, the help rate calculation unit 630 can also be configured to calculate the help rate of the page to be evaluated based on the single-channel help rate of each help channel, the help cost coefficient corresponding to each help channel, and / or the help attenuation coefficient used to attenuate the abnormal growth of help requests.

[0111] The second page determination unit 640 is configured to determine the pages to be deployed with help services based on the help request rate of each page to be evaluated. The help service is used to resolve user-initiated help requests.

[0112] Reference above Figures 1 to 6 This specification describes embodiments of a method and apparatus for discovering a need to deploy a help-seeking service, according to examples of these embodiments.

[0113] The apparatus for detecting a need for help service deployment, as described in the embodiments of this specification, can be implemented in hardware, software, or a combination of hardware and software. Taking software implementation as an example, as a logical device, it is formed by the processor of its host device reading the corresponding computer program instructions from the memory into memory and executing them. In the embodiments of this specification, the apparatus for detecting a need for help service deployment can, for example, be implemented using an electronic device.

[0114] Figure 7 A block diagram of an electronic device 700 for implementing a page discovery method according to an embodiment of this specification is shown.

[0115] like Figure 7 As shown, the electronic device 700 may include at least one processor 710, a memory (e.g., non-volatile memory) 720, a RAM 730, and a communication interface 740, and the at least one processor 710, memory 720, RAM 730, and communication interface 740 are connected together via a bus 750. The at least one processor 710 executes at least one computer-readable instruction (i.e., the elements implemented in software above) stored or encoded in the memory.

[0116] In one embodiment, computer-executable instructions are stored in memory, which, when executed, cause at least one processor 710 to: acquire page access data, the page access data including data of at least one of three dimensions: business, user, and page; determine pages to be evaluated based on the page access data; calculate the help rate of each page to be evaluated based on historical help data corresponding to the help channels deployed on the page to be evaluated; and determine pages to deploy help services based on the help rates of each page to be evaluated, the help services being used to resolve user-initiated help requests.

[0117] It should be understood that the computer-executable instructions stored in memory, when executed, cause at least one processor 710 to perform the above-described combinations in the various embodiments of this specification. Figure 1-6 The description includes various operations and functions.

[0118] According to one embodiment, a program product, such as a machine-readable medium, is provided. The machine-readable medium may have instructions (i.e., the elements implemented in software as described above), which, when executed by a machine, cause the machine to perform the above-described combinations of the various embodiments of this specification. Figure 1-6 The description includes various operations and functions.

[0119] Specifically, a system or apparatus equipped with a readable storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer or processor of the system or apparatus can read and execute the instructions stored in the readable storage medium.

[0120] In this case, the program code itself, which can be read from a readable medium, can perform the functions of any of the above embodiments. Therefore, the machine-readable code and the readable storage medium storing the machine-readable code constitute a part of the present invention.

[0121] The computer program code required for the operation of each part of this manual can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB, .NET, and Python; conventional procedural programming languages ​​such as C, Visual Basic 2003, Perl, COBOL 2002, PHP, and ABAP; dynamic programming languages ​​such as Python, Ruby, and Groovy; or other programming languages. This program code can run on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer via any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service, such as Software as a Service (SaaS).

[0122] Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer or the cloud via a communication network.

[0123] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0124] Not all steps and units in the above process and system structure diagrams are mandatory; some steps or units can be omitted as needed. The execution order of each step is not fixed and can be determined as required. The device structure described in the above embodiments can be a physical structure or a logical structure. That is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or they may be jointly implemented by certain components in multiple independent devices.

[0125] The term "exemplary" as used throughout this specification means "serving as an example, instance, or illustration" and does not imply that it is "preferred" or "advantageous" over other embodiments. Detailed descriptions are included for the purpose of providing an understanding of the described techniques. However, these techniques may be practiced without these detailed descriptions. In some instances, well-known structures and apparatuses are shown in block diagram form to avoid obscuring the concepts of the described embodiments.

[0126] The optional embodiments of the present specification have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present specification are not limited to the specific details in the above embodiments. Within the scope of the technical concept of the embodiments of the present specification, various simple modifications can be made to the technical solutions of the embodiments of the present specification, and these simple modifications all fall within the protection scope of the embodiments of the present specification.

[0127] The foregoing description of this specification is provided to enable any person skilled in the art to implement or use the content of this specification. Various modifications to the content of this specification will be apparent to those skilled in the art, and the general principles defined herein can be applied to other variations without departing from the scope of protection of this specification. Therefore, this specification is not limited to the examples and designs described herein, but is consistent with the widest scope of the principles and novel features disclosed herein.

Claims

1. A method for discovering pages that require the deployment of help-seeking services, comprising: Obtain page access data, which includes at least one of page dimension data, user dimension data, and business dimension data. The page dimension data includes the pages that have been accessed. The user dimension data includes the pages accessed by each user, the time of accessing the pages, and the requests for help initiated by each user on the pages. The business dimension data includes multiple sets of business dimension data categorized according to various business types. The business dimension data corresponding to each business type includes the page information corresponding to that business and the user information related to that business. The user information related to that business includes user dimension data. The pages to be evaluated are determined based on the page access data. For each page to be evaluated, the help rate of the page to be evaluated is calculated based on the historical help data of the help channels deployed on that page. as well as The pages to be deployed with help services are determined based on the help rate of each page to be evaluated. These help services are used to resolve user-initiated requests for help.

2. The method as described in claim 1, wherein, Based on the page access data, the pages to be evaluated include: When the page access data includes user-dimensional data, the user requesting help is determined based on the user-initiated help request in the user-dimensional data; and The page to be evaluated is determined based on the pages visited by the user seeking help, which are included in the user dimension data.

3. The method as described in claim 2, wherein, The users who initiated the requests for help based on the user dimension data include: The user-dimensional data includes requests for help initiated by users, selected from the top-ranked requests in terms of quantity; and Users who initiate the selected requests for help are identified as requesting help users.

4. The method of claim 2, wherein, The pages to be evaluated are determined based on the user dimension data, including the pages visited by the user seeking help. Based on at least one of the following filtering conditions—specific business, specific page, and specified page access duration threshold—the page to be evaluated is selected from the pages accessed by the user seeking help, which are included in the user dimension data.

5. The method of claim 1, wherein, Based on the page access data, the pages to be evaluated include: When the page access data includes business dimension data, users related to a specific business are determined based on the business dimension data; and The page to be evaluated is determined based on the identified users in the business dimension data.

6. The method of claim 1, wherein, Based on the page access data, the pages to be evaluated include: When the page access data includes business dimension data, the business page with business attributes corresponding to the specified business is determined based on the business dimension data; and The page to be evaluated is determined based on the identified business pages.

7. The method of claim 1, wherein, Based on the page access data, the pages to be evaluated include: When the page access data includes user-dimensional data and / or business-dimensional data, filter out the requests for help initiated by users that rank second in terms of quantity from the page access data; For each selected request for help, determine the page that appears in the third specified position in terms of the number of times the request for help appears from the page access data; Cross-referencing the selected requests for help with the corresponding pages to determine the central page for the requests; and The page containing requests for help was identified as the page to be evaluated.

8. The method of claim 1, wherein, For each page to be evaluated, the help rate of that page is calculated based on the historical help data corresponding to the help channels deployed on that page, including: For each page to be evaluated, the single-channel help rate for each help channel deployed on that page is calculated based on historical help data. The request rate of the page to be evaluated is calculated based on the single-channel request rate of each of the aforementioned request channels.

9. The method of claim 8, wherein, The help rate of the page to be evaluated is calculated based on the single-channel help rate of each help channel, including: The request rate of the page to be evaluated is calculated based on at least one of the request cost coefficient corresponding to each request channel and the request attenuation coefficient used to attenuate abnormal growth in requests, as well as the single-channel request rate of each request channel.

10. The method of claim 1, wherein, The page access data obtained includes: Page access data is obtained using electronic forms, wherein the electronic forms are connected to the page access backend data system and are configured with data filtering conditions.

11. An apparatus for discovering pages that require the deployment of help services, comprising: The data acquisition unit acquires page access data, which includes at least one of page dimension data, user dimension data, and business dimension data. The page dimension data includes the pages that have been accessed. The user dimension data includes the pages accessed by each user, the time of accessing the pages, and the requests for help initiated by each user on the pages. The business dimension data includes multiple sets of business dimension data classified according to various business types. The business dimension data corresponding to each business type includes the page information corresponding to the business and the user information related to the business. The user information related to the business includes user dimension data. The first page determination unit determines the page to be evaluated based on the page access data. The help request rate calculation unit calculates the help request rate of each page to be evaluated based on the historical help request data corresponding to the help request channels deployed on that page. as well as The second page determination unit determines the page to be deployed with a help service based on the help rate of each page to be evaluated. The help service is used to resolve user-initiated requests for help.

12. An electronic device, comprising: At least one processor, a memory coupled to the at least one processor, and a computer program stored on the memory, wherein the at least one processor executes the computer program to implement the method as described in any one of claims 1-10.

13. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method as described in any one of claims 1-10.

14. A computer program product comprising a computer program that, when executed by a processor, implements the method as described in any one of claims 1-10.

Images