Method, device and computer readable storage medium for determining potential customers

Abstract

The application provides a potential customer determination method and device and a computer readable storage medium, relates to the field of data processing, and can improve the success rate of determining potential customers and improve the efficiency of determining potential customers. The method comprises the following steps: obtaining a user evaluation set of an application and an identifier of an issuer of the application; the download times of the application are greater than a first threshold value, and the user evaluation set comprises multiple user evaluations; determining a proportion of negative user evaluations of the application according to the user evaluation set of the application and a preset text classification model; the proportion of negative user evaluations is the ratio of the number of negative user evaluations in the user evaluation set to the number of all user evaluations in the user evaluation set, the label of the negative user evaluation is included in a preset label set, and the preset label set comprises multiple negative labels; in the case that the proportion of negative user evaluations of the application is greater than a second threshold value and the application does not use a cloud service, the issuer corresponding to the identifier is determined as a potential customer.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to methods, apparatus and computer-readable storage media for identifying potential customers. Background Technology

[0002] To promote cloud services and expand the number of users in the cloud service sector, it is necessary to identify potential customers for cloud services so that cloud services can be promoted to them in the future.

[0003] Existing customer acquisition methods identify potential customers through marketing activities conducted by marketers. For example, marketers identify potential customers through telephone marketing.

[0004] Existing methods for identifying potential customers based on marketing personnel are based on human intervention. Due to the uncertainty of human factors, the success rate of identifying potential customers by marketing personnel is sometimes low, resulting in low efficiency of existing methods. Summary of the Invention

[0005] This application provides a method, apparatus, and computer-readable storage medium for identifying potential customers, which can improve the success rate and efficiency of identifying potential customers.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] Firstly, a method for identifying potential customers is provided. This method includes: obtaining a set of user reviews for an application and the identifier of the application's publisher; the application's download count exceeding a first threshold, and the user review set including multiple user reviews; determining the proportion of negative user reviews for the application based on the user review set and a preset text classification model; the negative user review proportion is the ratio of the number of negative user reviews in the user review set to the total number of user reviews in the user review set, and the tags of the negative user reviews are included in a preset tag set, which includes multiple negative tags; if the proportion of negative user reviews for the application exceeds a second threshold and the application does not use cloud services, the publisher corresponding to the identifier is identified as a potential customer.

[0008] Based on this scheme, by obtaining a set of user reviews for the application, including multiple user evaluations, and the identifier of the application's publisher, the proportion of negative user reviews for the application is determined according to the user review set and a preset text classification model. If the proportion of negative user reviews for the application exceeds a second threshold and the application does not use cloud services, the publisher corresponding to that identifier is identified as a potential customer. Since cloud services significantly improve user experience, the absence of cloud services may lead to a poor user experience and a large number of negative user reviews. Therefore, compared to existing schemes that manually identify potential customers, this application's scheme, by determining the proportion of negative user reviews for the application, can improve the success rate of identifying potential customers and thus increase the efficiency of potential customer identification.

[0009] In conjunction with the first aspect, in some embodiments of the first aspect, determining the proportion of negative user reviews of an application based on a set of user reviews and a preset text classification model specifically includes: inputting multiple user reviews of the application into a preset text classification model to obtain a label for each user review; if the preset label set includes the labels of user reviews, determining that the user review is a negative user review, and obtaining the number of negative user reviews of the application; and using the ratio of the number of negative user reviews of the application to the number of all user reviews in the user review set as the proportion of negative user reviews of the application.

[0010] Based on this scheme, it is possible to determine the proportion of negative user reviews for an application by using the application's user review set and a preset text classification model.

[0011] In conjunction with the first aspect, in some embodiments of the first aspect, the method further includes: obtaining Internet Protocol (IP) addresses corresponding to multiple access traffic flows of the application within a preset time period; using the location information corresponding to the first IP address as the location information of the first server; the first IP address having the largest number of IP addresses among the multiple access traffic flows; and the first server being used to host the application's cloud services.

[0012] Based on this scheme, by obtaining the IP addresses corresponding to multiple access traffic of the application within a preset time period, and using the location information of the first IP address with the most access traffic as the location information of the first server, the distance between the cloud service server of the application and most users using the application can be minimized, thereby reducing the application's response time and improving the user experience of the application.

[0013] In conjunction with the first aspect, in some embodiments of the first aspect, the method further includes: obtaining the start time of multiple access traffic flows of the application within a preset time period; determining that the multiple access traffic flows of the application are periodic based on the start time of the multiple access traffic flows; determining a second server; the second server is used to carry the application's cloud services, the cloud services including a first function, the first function including periodically adjusting service capabilities.

[0014] Based on this scheme, by obtaining the start time of multiple access traffic events for an application within a preset time period, it is determined that the start time of these multiple access traffic events is periodic. By using a server that carries cloud services with periodic adjustment capabilities as a second server, the capabilities of the cloud service server carrying the application can be matched with the characteristics of the application's access traffic, thereby improving the user experience.

[0015] In conjunction with the first aspect, in some embodiments of the first aspect, the method further includes: obtaining the traffic size of multiple access traffic flows of the application within a preset time period; determining that the multiple access traffic flows of the application are bursty based on the traffic size of the multiple access traffic flows; determining a third server; the third server is used to carry the application's cloud services, the cloud services including a second function, the second function including bursty adjustment service capabilities.

[0016] Based on this solution, by obtaining the traffic volume of multiple access traffic events for an application within a preset time period, it is determined that multiple access traffic events are sudden. By using the server that carries cloud services with the ability to adjust services during sudden events as a third server, the capabilities of the cloud services carrying the application can be matched with the characteristics of the application's access traffic, thereby improving the user experience.

[0017] Secondly, a potential customer identification apparatus is provided for implementing the potential customer identification method described in the first aspect. The potential customer identification apparatus includes modules, units, or means corresponding to the above-described method. These modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the above-described functions.

[0018] In conjunction with the second aspect, in some embodiments of the second aspect, the device for determining potential customers includes: an acquisition module and a processing module; the acquisition module is used to acquire a set of user reviews for the application and an identifier of the application's publisher; the number of downloads of the application is greater than a first threshold, and the set of user reviews includes multiple user reviews; the processing module is used to determine the proportion of negative user reviews for the application based on the set of user reviews for the application and a preset text classification model; the proportion of negative user reviews is the ratio of the number of negative user reviews in the set of user reviews to the total number of user reviews in the set of user reviews, and the tags of the negative user reviews are included in a preset tag set, which includes multiple negative tags; the processing module is further used to identify the publisher corresponding to the identifier as a potential customer when the proportion of negative user reviews for the application is greater than a second threshold and the application does not use cloud services.

[0019] In conjunction with the second aspect, in some embodiments of the second aspect, the processing module is used to determine the proportion of negative user reviews of the application based on the application's user review set and a preset text classification model. Specifically, this includes: inputting multiple user reviews of the application into the preset text classification model to obtain a label for each user review; if the preset label set includes the labels of the user reviews, determining that the user review is a negative user review, and obtaining the number of negative user reviews of the application; and using the ratio of the number of negative user reviews of the application to the number of all user reviews in the user review set as the proportion of negative user reviews of the application.

[0020] In conjunction with the second aspect, in some embodiments of the second aspect, the processing module is further configured to: obtain Internet Protocol (IP) addresses corresponding to multiple access traffic flows of the application within a preset time period; use the location information corresponding to the first IP address as the location information of the first server; the first IP address has the largest number of IP addresses among the multiple access traffic flows; and the first server is used to carry the application's cloud services.

[0021] In conjunction with the second aspect, in some embodiments of the second aspect, the processing module is further configured to: obtain the start time of multiple access traffic flows of the application within a preset time period; determine that the multiple access traffic flows of the application are periodic based on the start time of the multiple access traffic flows; determine a second server; the second server is used to carry the cloud services of the application, the cloud services include a first function, the first function including periodically adjusting service capabilities.

[0022] In conjunction with the second aspect, in some embodiments of the second aspect, the processing module is further configured to: obtain the traffic size of multiple access traffic flows of the application within a preset time period; determine that the multiple access traffic flows of the application are bursty based on the traffic size of the multiple access traffic flows; determine a third server; the third server is used to carry the application's cloud services, the cloud services including a second function, the second function including bursty adjustment service capabilities.

[0023] Thirdly, a potential customer identification device is provided, comprising: at least one processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method provided by the first aspect and any possible implementation thereof.

[0024] Fourthly, a computer-readable storage medium is provided, wherein when instructions in the computer-readable storage medium are executed by a processor of a determining device of a potential customer, the determining device of the potential customer is enabled to perform the method provided by the first aspect and any possible implementation thereof.

[0025] Fifthly, a computer program product containing instructions is provided that, when run on a computer, enables the computer to perform the methods provided in the first aspect and any possible implementation thereof.

[0026] In a sixth aspect, a chip system is provided, comprising: a processor and an interface circuit; the interface circuit being configured to receive a computer program or instructions and transmit them to the processor; the processor being configured to execute the computer program or instructions to cause the chip system to perform the methods provided in the first aspect and any possible embodiments thereof.

[0027] The technical effects of any one of the second to sixth aspects can be found in the technical effects of the different embodiments of the first aspect described above, and will not be repeated here. Attached Figure Description

[0028] Figure 1 This application provides an architectural diagram of a potential customer identification system.

[0029] Figure 2 A flowchart illustrating a method for identifying potential customers provided in this application;

[0030] Figure 3 A flowchart illustrating yet another method for identifying potential customers provided in this application;

[0031] Figure 4 A flowchart illustrating yet another method for identifying potential customers provided in this application;

[0032] Figure 5 A flowchart illustrating yet another method for identifying potential customers provided in this application;

[0033] Figure 6 A flowchart illustrating yet another method for identifying potential customers provided in this application;

[0034] Figure 7 A schematic diagram of the structure of a determining device provided in this application;

[0035] Figure 8 A schematic diagram of another determining device provided in this application. Detailed Implementation

[0036] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0037] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0038] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0039] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0040] It is understood that in this application, "when," "if," and "if" all refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require that there must be a judgment action when implemented, nor do they imply any other limitations.

[0041] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0042] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments and implementation methods of the various embodiments in this application, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the implementation methods of the various embodiments are consistent and can be mutually referenced. The technical features in different embodiments and between the implementation methods of the various embodiments can be combined according to their inherent logical relationships to form new embodiments, implementation methods, implementation methods, or implementation approaches. The following embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0043] Figure 1 This application provides an architectural diagram of a system for identifying potential customers. The technical solutions of the embodiments of this application can be applied to... Figure 1 The system for identifying potential customers shown is as follows: Figure 1 As shown, the potential customer identification system 10 includes a potential customer identification device 11 and an electronic device 12.

[0044] The potential customer identification device 11 is directly or indirectly connected to the electronic device 12. This connection can be wired or wireless, and this application embodiment does not limit the connection.

[0045] The potential customer identification device 11 can be used to receive data from the electronic device 12.

[0046] Electronic device 12 can be used to send data to determination device 11 for potential customers.

[0047] It should be noted that the potential customer identification device 11 and the electronic device 12 can be independent devices or integrated into the same device; this application does not make specific limitations in this regard.

[0048] When the potential customer identification device 11 and the electronic device 12 are integrated into the same device, the communication method between the potential customer identification device 11 and the electronic device 12 is the same as the communication method between internal modules of the device. In this case, the communication process between the two is the same as that when the potential customer identification device 11 and the electronic device 12 are independent of each other.

[0049] In the following embodiments provided in this application, the potential customer identification device 11 and the electronic device 12 are described as being configured independently of each other.

[0050] In practical applications, the method for determining potential customers provided in this application embodiment can be applied to the potential customer determination device 11, or to the devices included in the potential customer determination device 11.

[0051] The following description, in conjunction with the accompanying drawings, uses the application of the potential customer determination method to the potential customer determination device 11 as an example to illustrate the potential customer determination method provided in this application embodiment.

[0052] For ease of description, the device for determining potential customers will be referred to simply as the determining device in the following detailed description of the embodiments of this application. This application will describe it uniformly here and will not repeat it hereafter.

[0053] Figure 2 A flowchart illustrating a method for identifying potential customers provided in this application is shown below. Figure 2 As shown, the method includes the following steps:

[0054] S201, Determine the set of user reviews for the application and the identifier of the application's publisher.

[0055] Among them, the number of app downloads exceeds the first threshold, and the user review set includes multiple user reviews.

[0056] It should be noted that the first threshold can be 10,000 times, or the first threshold can be 20,000 times, or the first threshold can be 30,000 times. This application does not limit it in this way.

[0057] User reviews are used to represent users' opinions on the application. For example, a user review could be "This application is terrible, it often lags when I use it," or "My data on another phone doesn't show up on this phone, the data in this application is too out of sync," or "The data I saved last time is gone for no reason, all the data is lost," or user reviews could be other kinds of evaluations, and this application does not limit them.

[0058] The identifier of the application's publisher is the identifier of the entity that publishes the application. For example, the identifier of the application's publisher can be Company A, or it can be Organization C. This application does not impose any restrictions on this.

[0059] As one possible implementation method, combined with Figure 1 The device determines that it receives a message from the electronic device 12, the message including a set of user reviews for the application, and the device determines the set of user reviews for the application from the message.

[0060] As another possible implementation, the device is identified when there is low traffic in one or more app stores and the scrapy crawler is used to crawl a collection of user reviews for the app.

[0061] S202, The determining device determines the proportion of negative user reviews for the application based on the application's user review set and a preset text classification model.

[0062] The negative user review percentage is the ratio of the number of negative user reviews in the user review set to the total number of user reviews in the user review set. The tags of negative user reviews are included in a preset tag set, which includes multiple negative tags.

[0063] It should be noted that the preset text classification model can be obtained by fine-tuning multi-classification based on the BERT pre-trained language model and multiple historical user reviews.

[0064] The preset tag set may include "application is prone to lag", "data is out of sync", "data is lost", "slow loading", or the preset tag set may include other negative tags, which is not limited in this application.

[0065] As one possible implementation, the device inputs multiple user reviews of the application into a preset text classification model to obtain a label for each user review; if the preset label set includes the labels of user reviews, the user review is determined to be a negative user review, and the number of negative user reviews of the application is obtained; the ratio of the number of negative user reviews of the application to the number of all user reviews in the user review set is taken as the proportion of negative user reviews of the application.

[0066] It should be noted that a detailed description of this possible implementation method can be found in the following sections of the specific implementation method of this application, and will not be repeated here.

[0067] S203. If the proportion of negative user reviews for the device in the application is greater than the second threshold and the application does not use cloud services, the issuer corresponding to the identifier will be identified as a potential customer.

[0068] It should be noted that the second threshold can be 0.4, or it can be 0.5, or it can be 0.6; this application does not impose any restrictions on this.

[0069] As one possible implementation, taking a second threshold of 0.4 as an example, if the determination device determines that the proportion of negative reviews for an application is greater than 0.4, it uses the Fiddler open-source packet capture tool to capture network data packets generated during application runtime. It then parses the request messages in the network data packets to obtain the Internet Protocol (IP) address of the application's server. If this IP address is not included in the set of IPs already in the cloud, it is determined that the application does not use cloud services, and the determination device identifies the issuer corresponding to this identifier as a potential customer. The set of IPs already in the cloud includes the IP addresses of servers of one or more applications that have used cloud services.

[0070] Based on this scheme, by obtaining a set of user reviews for the application, including multiple user evaluations, and the identifier of the application's publisher, the proportion of negative user reviews for the application is determined according to the user review set and a preset text classification model. If the proportion of negative user reviews for the application exceeds a second threshold and the application does not use cloud services, the publisher corresponding to that identifier is identified as a potential customer. Since cloud services significantly improve user experience, the absence of cloud services may lead to a poor user experience and a large number of negative user reviews. Therefore, compared to existing schemes that manually identify potential customers, this application's scheme, by determining the proportion of negative user reviews for the application, can improve the success rate of identifying potential customers and thus increase the efficiency of potential customer identification.

[0071] The above is a general description of the scheme of this application. The scheme of this application will be further described below with reference to the accompanying drawings.

[0072] In one design, Figure 3 A flowchart illustrating yet another method for identifying potential customers provided in this application, as shown below. Figure 3 As shown in the detailed embodiment of this application, S202 specifically includes the following steps:

[0073] S301, The device inputs multiple user reviews into a preset text classification model to obtain the label for each user review.

[0074] It should be noted that user reviews may include tags such as "application is prone to lag", "data is out of sync", "data is lost", "slow loading", "other", or other tags. This application does not impose any restrictions on this.

[0075] As one possible implementation, the determining device inputs multiple user reviews into a preset classification model. The preset classification model outputs a user review label mapping table. Based on the KServe inference service framework, the determining device encapsulates and determines the label for each user review from the user review label mapping table. The user review label mapping table includes the correspondence between each user review and each label.

[0076] S302. When the preset tag set includes tags for user reviews, the determining device determines that the user review is a negative user review and obtains the number of negative user reviews for the application.

[0077] As one possible implementation, taking the example of the preset tag set in S202 above, if a user review's tag is "the application is prone to lag", then the determining device determines that the user review is a negative user review. The determining device judges whether the tag of each user review is in the preset tag set and obtains the number of negative user reviews of the application.

[0078] S303, The determining device uses the ratio of the number of negative user reviews for the application to the total number of user reviews in the user review set as the percentage of negative user reviews for the application.

[0079] As one possible implementation, if the number of negative reviews for the application is 10 and the total number of user reviews in the user review set is 20, the determining device will use 10 / 20 = 0.5 as the proportion of negative user reviews for the application.

[0080] Based on this scheme, it is possible to determine the proportion of negative user reviews for an application by using the application's user review set and a preset text classification model.

[0081] In one design, Figure 4 A flowchart illustrating yet another method for identifying potential customers provided in this application, as shown below. Figure 4 As shown, the method for identifying potential customers provided in this application also includes the following steps:

[0082] S401. The device determines the IP addresses corresponding to multiple access traffic flows of the application within a preset time period.

[0083] It should be noted that the IP address corresponding to the access traffic can be the IP address of the base station that generated the access traffic. For example, if device A accesses the application through base station B, base station B will generate access traffic for the application, and the IP address of base station B is the IP address corresponding to the access traffic.

[0084] As one possible implementation method, combined with Figure 1 The device determines that it receives a message from the electronic device 12, which includes IP addresses corresponding to multiple access traffic flows of the application within a preset time period. The device then obtains the IP addresses corresponding to the multiple access traffic flows of the application within the preset time period from the message.

[0085] S402, The determining device uses the location information corresponding to the first IP address as the location information of the first server.

[0086] Among the multiple access traffic IP addresses, the first IP address has the most occurrences, and the first server is used to host the application's cloud services.

[0087] It should be noted that the location information corresponding to the first IP address can be the city where the first IP address is located, and correspondingly, the location information of the first server is the city where the first server is located.

[0088] As one possible implementation, the determining device is based on deep packet inspection (DPI) technology, which counts the number of each IP address in multiple access traffic IP addresses, and selects the IP address with the most counts as the first IP address.

[0089] For example, the IP addresses corresponding to multiple access traffic include 10 IP addresses, of which 5 are IP address number 1, 3 are IP address number 2, and 2 are IP address number 3. Then the determining device will use IP address number 1 as the first IP address.

[0090] Based on this scheme, by obtaining the IP addresses corresponding to multiple access traffic of the application within a preset time period, and using the location information of the first IP address with the most access traffic as the location information of the first server, the distance between the cloud service server of the application and most users using the application can be minimized, thereby reducing the application's response time and improving the user experience of the application.

[0091] In one design, Figure 5 A flowchart illustrating yet another method for identifying potential customers provided in this application, as shown below. Figure 5 As shown, the method for identifying potential customers provided in this application also includes the following steps:

[0092] S501, Determine the start time of multiple access traffic flows of the application within a preset time period.

[0093] As one possible implementation method, combined with Figure 1 The device determines that it receives a message from the electronic device 12, which includes the start time of multiple access traffic flows of the application within a preset time period, and obtains the start time of the multiple access traffic flows of the application within the preset time period from the message.

[0094] S502, The device determines that the multiple access traffic flows of the application are periodic based on the start time of the multiple access traffic flows.

[0095] As one possible implementation, the determining device is based on DPI technology. Multiple access traffic flows are arranged into a first access traffic set according to their start time. The first access traffic set is then expanded into a linear combination of trigonometric functions using Fourier transform, resulting in multiple expanded terms, each with its own Fourier coefficient. The largest Fourier coefficient among these expanded terms is set as a preset period. This preset period is used as the phase difference in the formula for calculating the autocorrelation coefficient, yielding the autocorrelation coefficient of the first access traffic set. If this autocorrelation coefficient is greater than a third threshold, then the multiple access traffic flows are determined to have periodicity.

[0096] S503, The determining device determines the second server.

[0097] The second server is used to host the cloud services of the application. The cloud services include the first function, which includes periodically adjusting service capabilities.

[0098] As one possible implementation, the device determines that the server carrying cloud services with periodic adjustment capabilities will serve as the second server.

[0099] Based on this scheme, by obtaining the start time of multiple access traffic events for an application within a preset time period, it is determined that the start time of these multiple access traffic events is periodic. By using a server that carries cloud services with periodic adjustment capabilities as a second server, the capabilities of the cloud services carrying the application can be matched with the characteristics of the application's access traffic, thereby improving the user experience.

[0100] In one design, Figure 6 A flowchart illustrating yet another method for identifying potential customers provided in this application, as shown below. Figure 6 As shown, the method for identifying potential customers provided in this application also includes the following steps:

[0101] S601, Determine the traffic volume of multiple access traffic applications within a preset time period obtained by the device.

[0102] As one possible implementation method, combined with Figure 1 The device determines that it receives a message from the electronic device 12, which includes the traffic size of multiple access traffic of the application within a preset time period, and obtains the traffic size of the multiple access traffic of the application within the preset time period from the message.

[0103] S602, The device determines that the multiple access traffic flows of the application are bursty based on the traffic size of the multiple access traffic flows.

[0104] As one possible implementation, the determination device is based on DPI technology to determine the standard deviation of daily access traffic, the standard deviation of weekly access traffic, the standard deviation of monthly access traffic, and the ratio of the maximum access traffic to the average access traffic. If the standard deviation of daily access traffic is greater than a fourth threshold, the standard deviation of weekly access traffic is greater than a fifth threshold, the standard deviation of monthly access traffic is greater than a sixth threshold, and the ratio of the maximum access traffic to the average access traffic is greater than a seventh threshold, then the determination device determines that multiple access traffic flows of the application are bursty.

[0105] S603, The device determines the third server.

[0106] The third server is used to host the cloud services of the application. The cloud services include a second function, which includes the ability to adjust services in case of emergencies.

[0107] As one possible implementation, the device will use a server that carries cloud services with the ability to provide bursty adjustment services as a third server.

[0108] Based on this solution, by obtaining the traffic volume of multiple access traffic events for an application within a preset time period, it is determined that multiple access traffic events are sudden. By using the server that carries cloud services with the ability to adjust services during sudden events as a third server, the capabilities of the cloud services carrying the application can be matched with the characteristics of the application's access traffic, thereby improving the user experience.

[0109] In one design, the method for determining potential customers provided in this application further includes: determining the service response speed of the application acquired by the device, and using the matplotlib plotting tool to create two-dimensional tables showing the correspondence between the size of the access traffic and the start time of the access traffic, the correspondence between the size of the access traffic and the IP address of the access traffic, and the correspondence between the size of the access traffic and the service response speed, so that the relevant data of the application's traffic can be analyzed intuitively in the future.

[0110] The foregoing mainly describes the solution provided by the embodiments of this application from the perspective of determining the method for identifying potential customers using a determining device. To achieve the above functions, the determining device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0111] This application embodiment can divide the determining device into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation. Furthermore, "module" here can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory executing one or more software or firmware programs, integrated logic circuits, and / or other devices that can provide the above functions.

[0112] When using functional module division Figure 7 A schematic diagram of a determining device is shown. Figure 7 As shown, the determining device 70 includes an acquisition module 701 and a processing module 702.

[0113] In some embodiments, the determining device 70 may further include a storage module ( Figure 7 (Not shown in the image) is used to store program instructions and data.

[0114] The acquisition module 701 is used to acquire the user review set of the application and the identifier of the application's publisher; the number of downloads of the application is greater than a first threshold, and the user review set includes multiple user reviews; the processing module 702 is used to determine the proportion of negative user reviews of the application based on the user review set and a preset text classification model; the proportion of negative user reviews is the ratio of the number of negative user reviews in the user review set to the total number of user reviews in the user review set, and the tags of negative user reviews are included in a preset tag set, which includes multiple negative tags; the processing module 702 is also used to identify the publisher corresponding to the identifier as a potential customer when the proportion of negative user reviews of the application is greater than a second threshold and the application does not use cloud services.

[0115] Optionally, the processing module 702 is used to determine the proportion of negative user reviews of the application based on the application's user review set and a preset text classification model. Specifically, it includes: inputting multiple user reviews of the application into the preset text classification model to obtain the label of each user review; if the preset label set includes the label of the user review, determining that the user review is a negative user review and obtaining the number of negative user reviews of the application; and taking the ratio of the number of negative user reviews of the application to the number of all user reviews in the user review set as the proportion of negative user reviews of the application.

[0116] Optionally, the processing module 702 is further configured to: obtain Internet Protocol (IP) addresses corresponding to multiple access traffic flows of the application within a preset time period; use the location information corresponding to the first IP address as the location information of the first server; the first IP address has the largest number of IP addresses among the multiple access traffic flows; and the first server is used to carry the application's cloud services.

[0117] Optionally, the processing module 702 is further configured to: obtain the start time of multiple access traffic flows of the application within a preset time period; determine that the multiple access traffic flows of the application are periodic based on the start time of the multiple access traffic flows; determine a second server; the second server is used to carry the application's cloud services, the cloud services including a first function, the first function including periodically adjusting service capabilities.

[0118] Optionally, the processing module 702 is further configured to: obtain the traffic size of multiple access traffic of the application within a preset time period; determine that the multiple access traffic of the application is bursty based on the traffic size of the multiple access traffic; determine a third server; the third server is used to carry the application's cloud services, the cloud services include a second function, the second function includes bursty adjustment service capabilities.

[0119] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0120] When the functions of the above modules are implemented in hardware... Figure 8 A schematic diagram of a determining device is shown. Figure 8 As shown, the determining device 80 includes a processor 801, a memory 802, and a bus 803. The processor 801 and the memory 802 can be connected via the bus 803.

[0121] Processor 801 is the control center of determining device 80. It can be a single processor or a collective term for multiple processing elements. For example, processor 801 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0122] As one embodiment, processor 801 may include one or more CPUs, for example Figure 8 CPU 0 and CPU 1 are shown in the diagram.

[0123] The memory 802 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0124] As one possible implementation, the memory 802 can exist independently of the processor 801. The memory 802 can be connected to the processor 801 via a bus 803 and is used to store instructions or program code. When the processor 801 calls and executes the instructions or program code stored in the memory 802, it can implement the method for determining potential customers provided in the embodiments of this application.

[0125] In another possible implementation, the memory 802 can also be integrated with the processor 801.

[0126] The 803 bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus can be divided into address bus, data bus, and control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0127] It should be pointed out that, Figure 8 The structure shown does not constitute a limitation on the determining device 80. Except... Figure 8 In addition to the components shown, the determining device 80 may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0128] As an example, combined Figure 7 The functions implemented by the acquisition module 701 and the processing module 702 in the determination device 70 are... Figure 8 The processor 801 in it has the same function.

[0129] Optional, such as Figure 8 As shown, the determining device 80 provided in this application embodiment may further include a communication interface 804.

[0130] Communication interface 804 is used to connect with other devices via a communication network. This communication network can be Ethernet, a wireless access network, a wireless local area network (WLAN), etc. Communication interface 804 may include a receiving unit for receiving data and a transmitting unit for transmitting data.

[0131] In one possible implementation, the communication interface 804 in the determining device 80 provided in this application embodiment can also be integrated into the processor 801, and this application embodiment does not specifically limit this.

[0132] As a possible product form, the determining device in the embodiments of this application can also be implemented using one or more field programmable gate arrays (FPGAs), programmable logic devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0133] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional units is used as an example. In practical applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the device can be divided into different functional units to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0134] This application also provides a computer-readable storage medium storing a computer program or instructions thereon, which, when executed, causes a computer to perform the various steps in the method flow shown in the above method embodiments.

[0135] Embodiments of this application provide a computer program product containing instructions that, when executed on a computer, cause the computer to perform the various steps in the method flow shown in the above-described method embodiments.

[0136] This application provides a chip system, including: a processor and an interface circuit; the interface circuit is used to receive computer programs or instructions and transmit them to the processor; the processor is used to execute the computer programs or instructions so that the chip system performs each step in the method flow shown in the above method embodiments.

[0137] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), registers, hard disks, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing, or any other form of computer-readable storage medium in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in a purpose-specific ASIC. In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0138] Since the determining device, computer-readable storage medium, and computer program product provided in this embodiment can be applied to the method for determining potential customers provided in this embodiment, the technical effects that can be obtained can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.

[0139] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, the disclosure, and the appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0140] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A method for identifying potential customers, characterized in that, The method includes: Obtain the user review set of the application and the identifier of the publisher of the application; the number of downloads of the application is greater than a first threshold, and the user review set includes multiple user reviews; The proportion of negative user reviews for the application is determined based on the application's user review set and a preset text classification model. The proportion of negative user reviews is the ratio of the number of negative user reviews in the user review set to the total number of user reviews in the user review set. The tags of the negative user reviews are contained in a preset tag set, which includes multiple negative tags. The preset text classification model is obtained by fine-tuning a multi-classification model based on a BERT pre-trained language model and multiple historical user reviews. If the proportion of negative user reviews for the application exceeds the second threshold and the application does not use cloud services, the issuer corresponding to the identifier will be identified as a potential customer.

2. The method according to claim 1, characterized in that, The step of determining the proportion of negative user reviews for the application based on the application's user review set and a preset text classification model specifically includes: The application's multiple user reviews are input into the preset text classification model to obtain the label for each user review; If the preset tag set includes tags for user reviews, the user review is determined to be a negative user review, and the number of negative user reviews for the application is obtained. The ratio of the number of negative user reviews for the application to the total number of user reviews in the user review set is taken as the percentage of negative user reviews for the application.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Obtain the Internet Protocol (IP) addresses corresponding to multiple access traffic flows of the application within a preset time period; The location information corresponding to the first IP address is used as the location information of the first server; the first IP address is the most numerous among the multiple access traffic IP addresses; the first server is used to carry the cloud services of the application.

4. The method according to claim 1 or 2, characterized in that, The method further includes: Obtain the start time of multiple access traffic events for the application within a preset time period; The multiple access traffic flows of the application are determined to be periodic based on the start time of the multiple access traffic flows; A second server is determined; the second server is used to host the cloud services of the application, the cloud services include a first function, the first function including periodically adjusting service capabilities.

5. The method according to claim 1 or 2, characterized in that, The method further includes: Obtain the traffic volume of multiple access traffic of the application within a preset time period; Based on the volume of the multiple access traffic, it is determined that the multiple access traffic of the application is bursty; A third server is identified; the third server is used to host the cloud services of the application, the cloud services include a second function, the second function including the ability to adjust services in case of sudden changes.

6. A device for identifying potential customers, characterized in that, The device for identifying potential customers includes: an acquisition module and a processing module; The acquisition module is used to acquire a set of user reviews for the application and the identifier of the publisher of the application; the number of downloads of the application is greater than a first threshold, and the set of user reviews includes multiple user reviews; The processing module is used to determine the proportion of negative user reviews for the application based on the application's user review set and a preset text classification model; the proportion of negative user reviews is the ratio of the number of negative user reviews in the user review set to the total number of user reviews in the user review set, the tags of the negative user reviews are contained in a preset tag set, and the preset tag set includes multiple negative tags; the preset text classification model is obtained by fine-tuning multi-classification based on a BERT pre-trained language model and multiple historical user reviews; The processing module is further configured to identify the issuer corresponding to the identifier as a potential customer when the proportion of negative user reviews of the application is greater than a second threshold and the application does not use cloud services.

7. The device for identifying potential customers according to claim 6, characterized in that, The processing module is used to determine the proportion of negative user reviews for the application based on the application's user review set and a preset text classification model, specifically including: The application's multiple user reviews are input into the preset text classification model to obtain the label for each user review; If the preset tag set includes tags for user reviews, the user review is determined to be a negative user review, and the number of negative user reviews for the application is obtained. The ratio of the number of negative user reviews for the application to the total number of user reviews in the user review set is taken as the percentage of negative user reviews for the application.

8. The device for identifying potential customers according to claim 6 or 7, characterized in that, The processing module is further configured to: Obtain the Internet Protocol (IP) addresses corresponding to multiple access traffic flows of the application within a preset time period; Use the location information corresponding to the first IP address as the location information of the first server; The first IP address is the most numerous among the multiple access traffic IP addresses; the first server is used to host the cloud services of the application.

9. The device for identifying potential customers according to claim 6 or 7, characterized in that, The processing module is further configured to: Obtain the start time of multiple access traffic events for the application within a preset time period; The multiple access traffic flows of the application are determined to be periodic based on the start time of the multiple access traffic flows; Determine the second server; The second server is used to host the cloud services of the application, the cloud services including a first function, the first function including periodically adjusting service capabilities.

10. The device for identifying potential customers according to claim 6 or 7, characterized in that, The processing module is further configured to: Obtain the traffic volume of multiple access traffic of the application within a preset time period; Based on the volume of the multiple access traffic, it is determined that the multiple access traffic of the application is bursty; Identify the third server; The third server is used to host the cloud services of the application, and the cloud services include a second function, which includes the ability to adjust services in case of sudden changes.

11. A device for identifying potential customers, characterized in that, The potential customer determination device includes: a processor coupled to a memory for storing programs or instructions that, when executed by the processor, cause the potential customer determination device to perform the method as described in any one of claims 1 to 5.

12. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed, they cause the computer to perform the method as described in any one of claims 1 to 5.

Images