Cloud product update method and system based on artificial intelligence

Abstract

The present invention relates to the field of artificial intelligence technology, and to a cloud product update method and system based on artificial intelligence. The present invention first obtains first feedback conversation flow data generated by a first product feedback user from a cloud product in a specific functional interval; and also obtains second feedback conversation flow data from a pre-experience scenario of at least one product function experience node. Then, based on these two types of conversation flow data, the system determines the user's focus item data in the specific functional interval of the cloud product. Next, these focus item data are analyzed using a long short-term memory network, and corresponding product optimization categories are generated, which not only considers the user's focus points, but also reflects the relationship characteristics between the user's focus words; these data and optimization categories are sent back to the cloud product to support the function optimization of the cloud product between different time nodes in the update stage, which can make the cloud product more in line with the user's actual needs and usage habits, thereby improving user experience and product competitiveness.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based cloud product updating method and system. Background Art

[0002] In today's context of rapid development of artificial intelligence and cloud computing services, user feedback plays a key role in product iteration and optimization. Traditional product improvement methods mainly rely on direct user surveys or feedback, which are often time-consuming and inefficient, and cannot capture users' actual usage and demand changes in a timely and accurate manner. Therefore, developing a method that can automatically obtain and analyze user feedback and guide product optimization has become an urgent problem that cloud product providers need to solve.

[0003] In the existing technology, feedback from cloud product users is usually collected through multiple channels such as online questionnaires, social media, and customer support conversations. These data are usually unstructured and contain rich but complex user opinions and feelings. Due to the lack of effective tools and algorithms, these valuable data resources are often not fully utilized to guide product optimization and updates. In addition, users may show different concerns and preferences in different product function areas, and traditional methods are difficult to accurately identify and optimize products in a targeted manner. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a cloud product updating method and system based on artificial intelligence.

[0005] According to one aspect of an embodiment of the present invention, a cloud product update method and system based on artificial intelligence are provided, the method comprising:

[0006] Acquire first feedback conversation flow data of a first product feedback user in a first cloud product functional section originating from a cloud product; and acquire second feedback conversation flow data of the first product feedback user in the first cloud product functional section originating from a pre-experience scenario of at least one product functional experience node;

[0007] Determining product concern item data of the first product feedback user in the first cloud product function section according to the first feedback conversation flow data and the second feedback conversation flow data;

[0008] Generating product optimization categories for the product attention item data of the first product feedback user in the first cloud product function section according to the long short-term memory network, and generating product optimization categories for the first product feedback user in the second cloud product function section;

[0009] The product focus item data and the product optimization category are generated for the cloud product, wherein the product optimization category reflects the relationship characteristics of the product focus words of product feedback users, the first cloud product function interval is a time node in the cloud product update phase, and the second cloud product function interval is a time node in the cloud product update phase that is located after the first cloud product function interval.

[0010] In a possible implementation, generating product optimization categories for the product attention item data of the first product feedback user in the first cloud product function section based on the long short-term memory network to generate product optimization categories for the first product feedback user in the second cloud product function section includes:

[0011] Obtaining a directed behavior vector of a first product feedback user in the first cloud product function interval, and a directed behavior vector and a product optimization category of a priori product feedback user in a cloud product update phase;

[0012] Determine the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determine a second product feedback user associated with the first product feedback user from among the prior product feedback users;

[0013] The product optimization category of the second cloud product functional section in feedback from the user of the second product is predicted based on the product optimization category of the second cloud product functional section in feedback from the user of the first product.

[0014] In a possible implementation, determining the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determining the second product feedback user associated with the first product feedback user from the prior product feedback users includes:

[0015] According to the prediction unit in the long short-term memory network, the correlation degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval is determined to generate the second product feedback user associated with the first product feedback user.

[0016] In a possible implementation, the long short-term memory network includes a plurality of different prediction units;

[0017] The step of determining the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval based on the prediction unit in the long short-term memory network to generate the second product feedback user associated with the first product feedback user includes:

[0018] Determine the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the multiple different prediction units in the long short-term memory network, and generate the second product feedback users generated by the multiple different prediction units respectively;

[0019] According to the influence coefficient of the prediction unit, the second product feedback users generated by the prediction units are merged to generate the second product feedback users associated with the first product feedback users.

[0020] In a possible implementation manner, the directed behavior vector of the user of the first product feedback includes directed behavior knowledge points and behavior connection relationships;

[0021] The step of fusing the second product feedback users generated by the prediction units according to the influence coefficients of the prediction units to generate the second product feedback users associated with the first product feedback users includes:

[0022] determining an influence coefficient of the prediction unit based on the number of the directed behavior knowledge points used by the prediction unit in the process of determining the relevance;

[0023] According to the influence coefficient of the prediction unit, the second product feedback users generated by the prediction units are merged to generate the second product feedback users associated with the first product feedback users.

[0024] In a possible implementation, the method further includes:

[0025] A product optimization category is generated for the product attention item data of the first product feedback user in the first cloud product function interval according to the long short-term memory network, and a first output category and a second output category of the product optimization category corresponding to the first product feedback user in the second cloud product function interval are generated, wherein the first output category reflects the predicted relevance of the product optimization category in the second cloud product function interval of the first product feedback user, and the second output category reflects the correlation between the first output category and the feedback conversation flow data in the product attention item data of the first product feedback user in the first cloud product function interval.

[0026] In a possible implementation, the method further includes:

[0027] Obtain product experience attributes of the prior product feedback users in the cloud product function area;

[0028] Classifying the directed behavior vector of the first product feedback user in the first cloud product function section according to the classification unit in the long short-term memory network, and generating a product experience attribute corresponding to the first product feedback user in the first cloud product function section;

[0029] The step of determining the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determining a second product feedback user associated with the first product feedback user from among the prior product feedback users, includes:

[0030] Based on the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function section, and based on the correlation between the product experience attributes of the first product feedback user and the prior product feedback user in the first cloud product function section, a second product feedback user associated with the first product feedback user is determined among the prior product feedback users.

[0031] According to another aspect of an embodiment of the present invention, a cloud product update method and system based on artificial intelligence are provided, the system comprising:

[0032] An acquisition module is configured to acquire first feedback conversation flow data of a first product feedback user in a first cloud product functional section from a cloud product; and acquire second feedback conversation flow data of the first product feedback user in a first cloud product functional section from a pre-experience scenario of at least one product functional experience node;

[0033] A determination module, configured to determine product concern item data of the first product feedback user in the first cloud product function section according to the first feedback conversation flow data and the second feedback conversation flow data;

[0034] The first generating module is used to generate product optimization categories for the product attention item data of the first product feedback user in the first cloud product function section according to the long short-term memory network, and generate product optimization categories for the first product feedback user in the second cloud product function section;

[0035] The second generation module is used to generate the product attention item data and the product optimization category for the cloud product, the product optimization category reflects the relationship characteristics of the product attention words of product feedback users, the first cloud product function interval is a time node in the cloud product update stage, and the second cloud product function interval is a time node in the cloud product update stage that is located after the first cloud product function interval.

[0036] According to another aspect of an embodiment of the present invention, a server is provided, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; the memory is used to store computer programs; the processor is used to implement the steps of any of the above-mentioned artificial intelligence-based cloud product update methods when executing the computer program.

[0037] According to another aspect of an embodiment of the present invention, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based cloud product update method can be executed.

[0038] In order to make the above-mentioned purposes, features and advantages of the embodiments of the present invention more obvious and easy to understand, the embodiments will be described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A schematic diagram showing components of a server provided by an embodiment of the present invention is shown;

[0041] Figure 2 A schematic diagram of a process of a cloud product update method based on artificial intelligence provided by an embodiment of the present invention is shown;

[0042] Figure 3 A functional module block diagram of an artificial intelligence-based cloud product update system provided in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0043] In order to enable students in the technical field to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. According to the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] The terms "first", "second", "third", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0045] Figure 1 An exemplary component diagram of a server 100 is shown. The server 100 may include one or more processors 104, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The server 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. Non-limitingly, for example, the storage medium 106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any storage medium may use any technology to store information. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent a fixed or removable component of the server 100. In one case, when the processor 104 executes an associated instruction stored in any storage medium or a combination of storage media, the server 100 may perform any operation of the associated instruction. The server 100 also includes one or more drive units 108 for interacting with any storage medium, such as a hard disk drive unit, an optical disk drive unit, etc.

[0046] The server 100 also includes input / output 110 (I / O) for receiving various inputs (via input unit 112) and for providing various outputs (via output unit 114). One specific output mechanism may include a presentation device 116 and an associated graphical user interface (GUI) 118. The server 100 may also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0047] The communication unit 122 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers 100, etc. governed by any protocol or combination of protocols.

[0048] Figure 2 The flowchart of the method and system for updating cloud products based on artificial intelligence provided by the embodiment of the present invention is shown. The method and system for updating cloud products based on artificial intelligence can be Figure 1 The server 100 shown in FIG. 1 is executed, and the detailed steps of the artificial intelligence-based cloud product update method are introduced as follows.

[0049] Step S110, obtaining first feedback conversation flow data of a first product feedback user in a first cloud product functional section from a cloud product, and obtaining second feedback conversation flow data of the first product feedback user in the first cloud product functional section from a pre-experience scenario of at least one product functional experience node.

[0050] Step S120: determining product concern item data of the first product feedback user in the first cloud product function section according to the first feedback conversation flow data and the second feedback conversation flow data.

[0051] Step S130, generating product optimization categories for the product focus item data of the first product feedback user in the first cloud product function section based on the long short-term memory network, and generating product optimization categories for the first product feedback user in the second cloud product function section.

[0052] Step S140, generating the product focus item data and the product optimization category for the cloud product, wherein the product optimization category reflects the relationship characteristics of the product focus words of product feedback users, the first cloud product function interval is a time node in the cloud product update phase, and the second cloud product function interval is a time node in the cloud product update phase that is located after the first cloud product function interval.

[0053] For example, suppose there is a cloud storage service product. In its functional area (such as file upload function), users may encounter various problems or experience certain highlights during use. At this time, users may submit feedback through the built-in feedback tool to express dissatisfaction with the slow upload speed or unfriendly interface, or appreciate certain usability features. These feedback information collected directly from the product constitute the first feedback session flow data.

[0054] Next, taking the cloud storage service as an example, one or more product experience nodes may be set up, such as online surveys, user interviews, or public testing environments, to allow users to use the function in a pre-experience scenario before it is officially launched. User behavior and feedback at these experience nodes will be captured, such as user suggestions for improvement when testing the new version of the file upload function, or opinions on the interface design. The data collected at the experience nodes constitute the second feedback session flow data.

[0055] On this basis, by analyzing the first and second feedback conversation flow data, the cloud storage service development team can identify the issues and features that users care about most, such as "upload speed", "file preview" or "interface friendliness". These concern data represent the main interests and problems of users when using specific functional areas of the product.

[0056] Finally, the long short-term memory network (LSTM) can be used to process and analyze the attention item data to generate product optimization categories. For example, if users frequently pay attention to the upload speed, the LSTM model may classify these feedbacks into the "performance optimization" category; if users often mention interface problems, the feedback may be classified into the "user interface improvement" category. Such classification helps the team arrange development plans more targeted.

[0057] As a result, in the next update phase of the cloud storage service (the second cloud product feature interval), the development team can plan the update content based on the generated "performance optimization" and "user interface improvement" categories. They may decide to upgrade server hardware, optimize code, or redesign the user interface. These decisions based on user feedback and machine learning analysis will eventually be reflected in the new version of the product, thereby enhancing the user experience.

[0058] That is, the above embodiments describe a user-centric cloud product optimization process, which starts with collecting user feedback, analyzes and generates optimization directions through machine learning models, and ultimately guides the actual update and improvement of the product.

[0059] Based on the above steps, user feedback data from different channels is collected and analyzed to guide the continuous optimization of the product. First, the first feedback conversation flow data generated by the first product feedback user from the cloud product in a specific functional interval is obtained; at the same time, the second feedback conversation flow data from the pre-experience scenario of at least one product function experience node is also obtained. Then, based on these two conversation flow data, the system determines the user's attention item data in the specific functional interval of the cloud product. Next, the long short-term memory network is used to analyze these attention item data and generate corresponding product optimization categories, which not only considers the user's attention points, but also reflects the relationship characteristics between the user's attention words. Finally, these data and optimization categories are sent back to the cloud product to support the function optimization of the cloud product between different time nodes in the update stage, which can make the cloud product more in line with the actual needs and usage habits of users, thereby improving user experience and product competitiveness.

[0060] In a possible implementation, generating product optimization categories for the product attention item data of the first product feedback user in the first cloud product function section based on the long short-term memory network to generate product optimization categories for the first product feedback user in the second cloud product function section includes:

[0061] Obtaining a directed behavior vector of a first product feedback user in the first cloud product function interval, and a directed behavior vector and a product optimization category of a priori product feedback user in a cloud product update phase;

[0062] Determine the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determine a second product feedback user associated with the first product feedback user from among the prior product feedback users;

[0063] The product optimization category of the second cloud product functional section in feedback from the user of the second product is predicted based on the product optimization category of the second cloud product functional section in feedback from the user of the first product.

[0064] In a possible implementation, determining the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determining the second product feedback user associated with the first product feedback user from the prior product feedback users includes:

[0065] According to the prediction unit in the long short-term memory network, the correlation degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval is determined to generate the second product feedback user associated with the first product feedback user.

[0066] In a possible implementation, the long short-term memory network includes a plurality of different prediction units;

[0067] The step of determining the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval based on the prediction unit in the long short-term memory network to generate the second product feedback user associated with the first product feedback user includes:

[0068] Determine the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the multiple different prediction units in the long short-term memory network, and generate the second product feedback users generated by the multiple different prediction units respectively;

[0069] According to the influence coefficient of the prediction unit, the second product feedback users generated by the prediction units are merged to generate the second product feedback users associated with the first product feedback users.

[0070] In a possible implementation manner, the directed behavior vector of the user of the first product feedback includes directed behavior knowledge points and behavior connection relationships;

[0071] The step of fusing the second product feedback users generated by the prediction units according to the influence coefficients of the prediction units to generate the second product feedback users associated with the first product feedback users includes:

[0072] determining an influence coefficient of the prediction unit based on the number of the directed behavior knowledge points used by the prediction unit in the process of determining the relevance;

[0073] According to the influence coefficient of the prediction unit, the second product feedback users generated by the prediction units are merged to generate the second product feedback users associated with the first product feedback users.

[0074] In a possible implementation, the method further includes:

[0075] A product optimization category is generated for the product attention item data of the first product feedback user in the first cloud product function interval according to the long short-term memory network, and a first output category and a second output category of the product optimization category corresponding to the first product feedback user in the second cloud product function interval are generated, wherein the first output category reflects the predicted relevance of the product optimization category in the second cloud product function interval of the first product feedback user, and the second output category reflects the correlation between the first output category and the feedback conversation flow data in the product attention item data of the first product feedback user in the first cloud product function interval.

[0076] In a possible implementation, the method further includes:

[0077] Obtain product experience attributes of the prior product feedback users in the cloud product function area;

[0078] Classifying the directed behavior vector of the first product feedback user in the first cloud product function section according to the classification unit in the long short-term memory network, and generating a product experience attribute corresponding to the first product feedback user in the first cloud product function section;

[0079] The step of determining the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determining a second product feedback user associated with the first product feedback user from among the prior product feedback users, includes:

[0080] Based on the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function section, and based on the correlation between the product experience attributes of the first product feedback user and the prior product feedback user in the first cloud product function section, a second product feedback user associated with the first product feedback user is determined among the prior product feedback users.

[0081] Figure 3 The functional module diagram of the cloud product update system 200 based on artificial intelligence provided by the embodiment of the present invention is shown. The functions implemented by the cloud product update system 200 based on artificial intelligence can correspond to the steps performed by the above method. The cloud product update system 200 based on artificial intelligence can be understood as the above server 100, or the processor of the server 100, or can be understood as a component independent of the above server 100 or the processor that implements the functions of the present invention under the control of the server 100, such as Figure 3 As shown, the functions of each functional module of the cloud product update system 200 based on artificial intelligence are explained in detail below.

[0082] The acquisition module 210 is used to acquire first feedback conversation flow data of a first product feedback user in a first cloud product functional section from a cloud product; and acquire second feedback conversation flow data of the first product feedback user in the first cloud product functional section from a pre-experience scenario of at least one product functional experience node;

[0083] A determination module 220, configured to determine product concern item data of the first product feedback user in the first cloud product function section according to the first feedback conversation flow data and the second feedback conversation flow data;

[0084] The first generating module 230 is used to generate product optimization categories for the product attention item data of the first product feedback user in the first cloud product function section according to the long short-term memory network, and generate product optimization categories for the first product feedback user in the second cloud product function section;

[0085] The second generation module 240 is used to generate the product attention item data and the product optimization category for the cloud product, the product optimization category reflects the relationship characteristics of the product attention words of the product feedback users, the first cloud product function interval is a time node in the cloud product update stage, and the second cloud product function interval is a time node in the cloud product update stage located after the first cloud product function interval.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0087] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, the embodiments should be considered exemplary and non-restrictive in all respects, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the present invention.

Claims

1. A cloud product update method based on artificial intelligence, characterized in that: The method comprises: Acquire first feedback conversation flow data of a first product feedback user in a first cloud product functional section originating from a cloud product; and acquire second feedback conversation flow data of the first product feedback user in the first cloud product functional section originating from a pre-experience scenario of at least one product functional experience node; Determining product concern item data of the first product feedback user in the first cloud product function section according to the first feedback conversation flow data and the second feedback conversation flow data; Generating product optimization categories for the product attention item data of the first product feedback user in the first cloud product function section according to the long short-term memory network, and generating product optimization categories for the first product feedback user in the second cloud product function section; generating the product attention item data and the product optimization category for the cloud product, wherein the product optimization category reflects the relationship characteristics of the product attention words of the product feedback user, the first cloud product function interval is a time node in the cloud product update phase, and the second cloud product function interval is a time node after the first cloud product function interval in the cloud product update phase; The generating of product optimization categories for the product attention item data of the first product feedback user in the first cloud product function section according to the long short-term memory network to generate the product optimization categories for the first product feedback user in the second cloud product function section includes: Obtaining a directed behavior vector of a first product feedback user in the first cloud product function interval, and a directed behavior vector and a product optimization category of a priori product feedback user in a cloud product update phase; Determine the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determine a second product feedback user associated with the first product feedback user from among the prior product feedback users; Predicting the product optimization category of the first product feedback user in the second cloud product functional section according to the product optimization category of the second product feedback user in the second cloud product functional section; The step of determining the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determining a second product feedback user associated with the first product feedback user from among the prior product feedback users, includes: Determine the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the prediction unit in the long short-term memory network, and generate the second product feedback user associated with the first product feedback user; The long short-term memory network includes a plurality of different prediction units; The step of determining the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval based on the prediction unit in the long short-term memory network to generate the second product feedback user associated with the first product feedback user includes: Determine the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the multiple different prediction units in the long short-term memory network, and generate the second product feedback users generated by the multiple different prediction units respectively; According to the influence coefficient of the prediction unit, the second product feedback users generated by the prediction units are merged to generate the second product feedback user associated with the first product feedback user.

2. The method for updating cloud products based on artificial intelligence according to claim 1, characterized in that: The directed behavior vector of the user fed back by the first product includes directed behavior knowledge points and behavior connection relationships; The step of fusing the second product feedback users generated by the prediction units according to the influence coefficients of the prediction units to generate the second product feedback users associated with the first product feedback users includes: determining an influence coefficient of the prediction unit based on the number of the directed behavior knowledge points used by the prediction unit in the process of determining the relevance; According to the influence coefficient of the prediction unit, the second product feedback users generated by the prediction units are merged to generate the second product feedback user associated with the first product feedback user.

3. The method for updating cloud products based on artificial intelligence according to any one of claims 1 to 2, characterized in that: The method further comprises: A product optimization category is generated for the product attention item data of the first product feedback user in the first cloud product function interval according to the long short-term memory network, and a first output category and a second output category of the product optimization category corresponding to the first product feedback user in the second cloud product function interval are generated, wherein the first output category reflects the predicted relevance of the product optimization category in the second cloud product function interval of the first product feedback user, and the second output category reflects the correlation between the first output category and the feedback conversation flow data in the product attention item data of the first product feedback user in the first cloud product function interval.

4. The method for updating cloud products based on artificial intelligence according to claim 1, characterized in that: The method further comprises: Obtain product experience attributes of the prior product feedback users in the cloud product function area; Classifying the directed behavior vector of the first product feedback user in the first cloud product function section according to the classification unit in the long short-term memory network, and generating a product experience attribute corresponding to the first product feedback user in the first cloud product function section; The step of determining the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determining a second product feedback user associated with the first product feedback user from among the prior product feedback users, includes: Based on the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function section, and based on the correlation between the product experience attributes of the first product feedback user and the prior product feedback user in the first cloud product function section, a second product feedback user associated with the first product feedback user is determined among the prior product feedback users.

5. A cloud product update system based on artificial intelligence, characterized in that: include: An acquisition module, configured to acquire first feedback conversation flow data from a first product feedback user of a cloud product in a first cloud product functional area; and obtaining second feedback conversation flow data of the first product feedback user in the first cloud product function section originating from a pre-experience scenario of at least one product function experience node; A determination module, configured to determine product concern item data of the first product feedback user in the first cloud product function section according to the first feedback conversation flow data and the second feedback conversation flow data; A first generating module is used to generate product optimization categories for the product attention item data of the first product feedback user in the first cloud product function section according to the long short-term memory network, and generate product optimization categories for the first product feedback user in the second cloud product function section; a second generating module, configured to generate the product attention item data and the product optimization category for the cloud product, wherein the product optimization category reflects the relationship characteristics of the product attention words of the product feedback users, the first cloud product function interval is a time node in the cloud product update phase, and the second cloud product function interval is a time node after the first cloud product function interval in the cloud product update phase; The generating of product optimization categories for the product attention item data of the first product feedback user in the first cloud product function section according to the long short-term memory network to generate the product optimization categories for the first product feedback user in the second cloud product function section includes: Obtaining a directed behavior vector of a first product feedback user in the first cloud product function interval, and a directed behavior vector and a product optimization category of a priori product feedback user in a cloud product update phase; Determine the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determine a second product feedback user associated with the first product feedback user from among the prior product feedback users; Predicting the product optimization category of the first product feedback user in the second cloud product functional section according to the product optimization category of the second product feedback user in the second cloud product functional section; The step of determining the correlation between the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the long short-term memory network, and determining a second product feedback user associated with the first product feedback user from among the prior product feedback users, includes: Determine the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the prediction unit in the long short-term memory network, and generate the second product feedback user associated with the first product feedback user; The long short-term memory network includes a plurality of different prediction units; The step of determining the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval based on the prediction unit in the long short-term memory network to generate the second product feedback user associated with the first product feedback user includes: Determine the association degree of the directed behavior vectors of the first product feedback user and the prior product feedback user in the first cloud product function interval according to the multiple different prediction units in the long short-term memory network, and generate the second product feedback users generated by the multiple different prediction units respectively; According to the influence coefficient of the prediction unit, the second product feedback users generated by the prediction units are merged to generate the second product feedback user associated with the first product feedback user.

6. A server, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; the processor is used to implement the steps of the artificial intelligence-based cloud product update method described in any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the artificial intelligence-based cloud product update method described in any one of claims 1 to 4 are implemented.

Images