Server and demand analysis report generation method

Abstract

The present application relates to a server and a demand analysis report generation method, the server comprising: a communication device configured to communicate with a data source; the at least one processor is connected with the communication device and is configured to obtain at least one piece of comment data for the target product from the data source; selecting a target agent for processing the comment data from the at least one agent according to the comment data; inputting the comment data into the target agent to obtain comment analysis data of the comment data; and generating a demand analysis report for the target product according to the comment analysis data corresponding to the at least one piece of comment data. The demand analysis report can be automatically generated according to the comment data of the target product, manual analysis of the comment data is not needed, and the analysis efficiency can be improved. And subjective deviation caused by manual analysis is reduced, and the analysis accuracy can be improved. As the demand analysis report is automatically generated, a lot of manpower and material resources are not needed, and the cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to a server and a method for generating a demand analysis report. Background Art

[0002] E-commerce platforms have become the primary shopping channel for consumers, and product reviews have become a key factor influencing purchasing decisions. According to industry statistics, over 90% of consumers read reviews before making a purchase, and 82% consider reviews to be an important factor in their purchasing decisions. For sellers and manufacturers, review data contains a wealth of valuable information on product quality, user experience, and market demand.

[0003] However, with the expansion of e-commerce, the volume of review data has exploded. A popular product on a major e-commerce platform may accumulate thousands or even tens of thousands of reviews. Currently, manual analysis of review data is the primary method, which is inefficient and subject to subjective factors, resulting in low accuracy. Summary of the Invention

[0004] This application provides a server and a demand analysis report generation method, which can automatically generate a demand analysis report based on comment data, thereby improving analysis efficiency and accuracy compared to manual analysis methods.

[0005] In a first aspect, some embodiments provide a server, including:

[0006] a communication device configured to communicate with a data source;

[0007] At least one processor is connected to the communication device and is configured to:

[0008] Obtain at least one review data for the target product from the data source;

[0009] Selecting a target intelligent agent for processing the comment data from at least one intelligent agent according to the comment data;

[0010] Input the comment data into the target agent to obtain comment analysis data of the comment data;

[0011] Generate a demand analysis report for a target product based on the review analysis data corresponding to at least one piece of review data.

[0012] In some embodiments, for each comment data, the server selects a target agent for processing the comment data from at least one agent based on the comment data, thereby improving the compatibility of the selected target agent with the comment data. In addition, since the number of target agents selected from at least one agent is not limited, the diversity of agents analyzing the comment data is further improved. Accordingly, the comment data is input into the corresponding diverse target agents to obtain corresponding comment analysis data, thereby improving the compatibility and diversity of the comment analysis data output by the target agent with the comment data, and further improving the accuracy and richness of the comment analysis data corresponding to the comment data. Accordingly, based on the comment analysis data corresponding to each comment data, a demand analysis report for the target product is generated, which can integrate different comment data for the target product from different agents, thereby improving the accuracy and richness of the content included in the demand analysis. Furthermore, since the demand analysis report can guide decisions such as product development, marketing strategies and customer service, it lays the foundation for the optimization and improvement of the product ecology of the target product. In addition, since the above process does not require manual analysis of the comment data, it not only improves the analysis efficiency, but also reduces the subjective bias caused by human analysis, improves the accuracy of the analysis results, and does not require a large amount of manpower and material resources, thereby reducing costs.

[0013] In a second aspect, some embodiments provide a method for generating a demand analysis report, including:

[0014] Obtain at least one review data for the target product from the data source;

[0015] Selecting a target intelligent agent for processing the comment data from at least one intelligent agent according to the comment data;

[0016] Input the comment data into the target agent to obtain comment analysis data of the comment data;

[0017] Generate a demand analysis report for a target product based on the review analysis data corresponding to at least one piece of review data.

[0018] In some embodiments, for each piece of review data, a target agent is selected from at least one agent to process the review data based on the review data, thereby improving the compatibility of the selected target agent with the review data. Furthermore, since the number of target agents selected from the at least one agent is unlimited, the diversity of agents analyzing the review data is further increased. Accordingly, the review data is input into the corresponding diverse target agents to generate corresponding review analysis data, thereby improving the compatibility and diversity of the review analysis data output by the target agents with the review data, and thereby improving the accuracy and richness of the review analysis data corresponding to the review data. Accordingly, based on the review analysis data corresponding to each piece of review data, a demand analysis report for the target product is generated, which can integrate the different review data for the target product from different agents, thereby improving the accuracy and richness of the content included in the demand analysis. Furthermore, since the demand analysis report can guide decisions such as product development, marketing strategies, and customer service, it lays a foundation for optimizing and improving the product ecosystem of the target product. Furthermore, since the above process does not require manual analysis of the review data, it not only improves analysis efficiency but also reduces the subjective bias caused by manual analysis, improves the accuracy of the analysis results, and eliminates the need for significant human and material resources, thus reducing costs.

[0019] In a third aspect, some embodiments further provide a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in some embodiments of the first aspect are implemented.

[0020] In a fourth aspect, some embodiments further provide a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method provided in some embodiments of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 A schematic diagram of an operation scenario between a display device and a control device in one embodiment;

[0023] Figure 2 A schematic diagram of the hardware configuration of a display device in one embodiment;

[0024] Figure 3 A schematic diagram of the hardware configuration of a control device in one embodiment;

[0025] Figure 4 A schematic diagram of software configuration of a display device in one embodiment;

[0026] Figure 5 A flowchart of a method for generating a demand analysis report in one embodiment is shown;

[0027] Figure 6 1 is a flow chart of the steps for selecting a target agent in one embodiment;

[0028] Figure 7 1 is a flow chart of the steps for selecting a target agent in one embodiment;

[0029] Figure 8 A flowchart of steps for generating a demand analysis report in one embodiment;

[0030] Figure 9 A flowchart of steps for generating a demand analysis report in one embodiment;

[0031] Figure 10 Schematic diagram of a flow chart of steps for obtaining target evaluation and analysis data in one embodiment;

[0032] Figure 11 A flowchart of steps for generating a demand analysis report in one embodiment;

[0033] Figure 12 A flowchart of a method for generating a demand analysis report in one embodiment is shown;

[0034] Figure 13 It is a structural block diagram of a demand analysis report generating device in one embodiment;

[0035] Figure 14 FIG. 4 is a diagram showing the internal structure of a server in one embodiment. DETAILED DESCRIPTION

[0036] The following embodiments are described in detail, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numbers in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following embodiments are not intended to represent all possible implementations consistent with the present application. They are merely examples of systems and methods consistent with certain aspects of the present application, as detailed in the claims.

[0037] It should be noted that the brief descriptions of terms in this application are only for the purpose of facilitating the understanding of the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and usual meanings.

[0038] In the specification and claims of this application and the accompanying drawings, the terms "first," "second," "third," etc. are used to distinguish similar or similar objects or entities, and are not necessarily intended to limit a particular order or sequence, unless otherwise noted. It should be understood that the terms used in this manner are interchangeable under appropriate circumstances.

[0039] The terms "comprise," "comprises," and "having," and any variations thereof, are intended to cover but not exclude inclusion; for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0040] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functionality associated with that element.

[0041] In some embodiments, the target product may include, but is not limited to, a display device, a projection device, an air conditioning device, a refrigerator device, etc. The following description uses a display device as an example, which should not be construed as a specific limitation on the target product.

[0042] For example, a display device generally refers to a device capable of displaying images and processing data. For example, display devices include but are not limited to smart TVs, mobile terminals, computers, monitors, advertising screens, wearable devices, virtual reality devices, augmented reality devices, etc.

[0043] Figure 1 FIG. 1 is a schematic diagram of an operation scenario between a display device and a control device in one embodiment. Figure 1 As shown in FIG, a user can operate the display device 200 through touch operation, the mobile terminal 300 and the control device 100. For example, the control device 100 can be a remote controller, a stylus pen, a handle, etc.

[0044] The mobile terminal 300 can function as a control device for performing human-computer interaction between a user and the display device 200. The mobile terminal 300 can also function as a communication device for establishing a communication connection with the display device 200 and exchanging data. In some embodiments, the mobile terminal 300 can install software applications with the display device 200, enabling connection and communication via a network communication protocol, enabling one-to-one control operations and data communication. Audio and video content displayed on the mobile terminal 300 can also be transmitted to the display device 200 for synchronized display.

[0045] like Figure 1 As shown in FIG, the display device 200 also communicates data with the server 400 through various communication methods. The display device 200 may be allowed to communicate via a local area network (LAN), a wireless local area network (WLAN), and other networks.

[0046] The display device 200 may provide a broadcast receiving television function, and may also additionally provide an intelligent network television function with a computer support function, including but not limited to network television, smart TV, Internet Protocol television (IPTV), etc.

[0047] Figure 2 Some embodiments of this application provide Figure 1 2 is a block diagram of the hardware configuration of the display device 200.

[0048] In some embodiments, the display device 200 may include at least one of a tuner 210, a communication device 220, a detector 230, a device interface 240, a controller 250, a display 260, an audio output device 270, a memory, a power supply, and a user input interface.

[0049] In some embodiments, detector 230 is used to collect signals from the external environment or external interactions. For example, detector 230 may include a light receiver, such as a sensor for collecting ambient light intensity; or an image collector, such as a camera, for collecting external environmental scenes, user attributes, or user interaction gestures; or a sound collector, such as a microphone, for receiving external sounds.

[0050] In some embodiments, the display 260 includes a display component for presenting images and a driver component for driving image display. The display 260 is used to receive image signals output from the controller 250 for display. For example, the display 260 can be used to display video content, image content, and components of a menu control interface and a user control UI interface.

[0051] In some embodiments, the communication device 220 is a component used to communicate with an external device or server 400 according to various communication protocol types. The display device 200 can be provided with multiple communication devices 220 depending on the supported communication methods. For example, if the display device 200 supports wireless network communication, the display device 200 can be provided with a communication device 220 including WiFi functionality. If the display device 200 supports Bluetooth connection communication, the display device 200 needs to be provided with a communication device 220 including Bluetooth functionality.

[0052] The communication device 220 can establish a communication connection between the display device 200 and an external device or server 400 via a wireless or wired connection. A wired connection can connect the display device 200 to an external device via a data cable, an interface, or other components. A wireless connection can connect the display device 200 to an external device via a wireless signal or wireless network. The display device 200 can establish a connection with an external device directly or indirectly through a gateway, router, or connection device.

[0053] In some embodiments, the controller 250 may include at least one of a central processing unit (CPU), a video processor, an audio processor, a graphics processor, and a power processor, and first to nth interfaces for input / output. The controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in a memory. The controller 250 controls the overall operation of the display device 200.

[0054] In some embodiments, the controller 250 and the tuner 210 may be located in different separate devices, that is, the tuner 210 may also be located in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0055] In some embodiments, the user may input a user command through a graphical user interface (GUI) displayed on the display 260 , and the user input interface receives the user input command through the graphical user interface (GUI).

[0056] In some embodiments, the audio output device 270 may be a local speaker of the display device 200, or an external audio output device connected to the display device 200. For the external audio output device connected to the display device 200, the display device 200 may further be provided with an external audio output terminal, through which the audio output device may be connected to the display device 200 to output the sound of the display device 200.

[0057] In some embodiments, the user input interface 280 may be configured to receive instructions from a user.

[0058] Figure 3 Some embodiments of this application provide Figure 1 FIG. 1 is a block diagram of the hardware configuration of the control device 100. Figure 3 As shown, the control device 100 may include: a controller 110, a communication interface 130, a user input / output interface, a memory, and a power supply.

[0059] The control device 100 is configured to control the display device 200 , and can receive user input operation instructions, and convert the operation instructions into instructions that the display device 200 can recognize and respond to, playing the role of an interactive intermediary between the user and the display device 200 .

[0060] In some embodiments, the control device 100 may be a smart device. For example, the control device 100 may be installed with various applications for controlling the display device 200 according to user needs.

[0061] In some embodiments, as Figure 1 As shown, the mobile terminal 300 or other intelligent electronic devices can play a similar function as the control device 100 after installing the application for controlling the display device 200 .

[0062] The controller 110 includes a processor 112, RAM 113, ROM 114, a communication interface 130, and a communication bus. The controller 110 is used to control the operation and operation of the control device 100, as well as the communication and cooperation between internal components and external and internal data processing functions.

[0063] The communication interface 130 communicates control signals and data signals with the display device 200 under the control of the controller 110. The communication interface 130 may include at least one of a WiFi chip 131, a Bluetooth module 132, an NFC module 133, or other near field communication modules.

[0064] The user input / output interface 140 includes at least one of a microphone 141 , a touch panel 142 , a sensor 143 , a button 144 and other input interfaces.

[0065] In some embodiments, the control device 100 includes at least one of a communication interface 130 and an input / output interface 140. The control device 100 is configured with the communication interface 130, such as a WiFi, Bluetooth, or NFC module, which can encode user input commands via the WiFi protocol, Bluetooth protocol, or NFC protocol and send them to the display device 200.

[0066] The memory 190 is used to store various operating programs, data and applications for driving and controlling the control device 100 under the control of the controller. The memory 190 can store various control signal instructions input by the user.

[0067] The power supply 180 is used to provide operating power support for each component of the control device 100 under the control of the controller.

[0068] To facilitate user interaction, in some embodiments, the display device 200 may run an operating system. An operating system is a computer program used to manage and control the hardware and software resources of the display device 200. The operating system may provide a user interface (control the display device), allow the user to interact with the display device 200, and support the running of various application programs.

[0069] It should be noted that the operating system can be a native operating system based on a specific operating platform, a third-party operating system deeply customized based on a specific operating platform, or an independent operating system specially developed for display devices.

[0070] The operating system can be divided into different modules or layers according to the functions implemented, e.g. Figure 4 As shown, in some embodiments, the system is divided into four layers, from top to bottom, namely the application layer (abbreviated as "application layer"), the application framework layer (abbreviated as "framework layer"), the system library layer and the kernel layer.

[0071] In some embodiments, the application layer provides services and interfaces for applications, enabling the display device 200 to run applications and interact with the user based on the applications. The application layer can host at least one application, which can include built-in window programs, system settings programs, clock programs, and the like, or applications developed by third-party developers. In specific implementations, the application packages in the application layer are not limited to the examples above.

[0072] The framework layer provides applications with an application programming interface (API) and programming framework. The application framework layer includes predefined functions. The application framework layer acts as a processing center, determining the actions taken by applications in the application layer. Through the API, applications can access system resources and services during execution.

[0073] like Figure 4As shown, in the embodiment of the present application, the application framework layer includes a view system, managers, content providers, etc., wherein the view system can design and implement the interface and interaction of the application, and the view system includes lists, grids, text boxes, buttons, etc. The manager includes at least one of the following modules: an activity manager for interacting with all activities running in the system; a location manager for providing system services or applications with access to the system location service; a package manager for retrieving various information related to the application packages currently installed on the device; a notification manager for controlling the display and clearing of notification messages; and a window manager for managing icons, windows, toolbars, wallpapers, and desktop widgets on the user interface.

[0074] In some embodiments, the activity manager is used to manage the lifecycle of each application and common navigation back functions, such as controlling application exit, opening, and back. The window manager is used to manage all window programs, such as obtaining the display screen size, determining whether there is a status bar, locking the screen, taking screenshots, and controlling changes in display windows, such as shrinking, shaking, or distorting the display window.

[0075] In some embodiments, the system runtime layer can provide support for the framework layer. When the framework layer is used, the operating system will run the instruction library contained in the system runtime layer, such as the C / C++ instruction library, to implement the functions to be implemented by the framework layer.

[0076] In some embodiments, the kernel layer is a functional layer between the hardware and software of the display device 200. The kernel layer can implement functions such as hardware abstraction, multitasking, and memory management. Figure 4 As shown, the kernel layer can be configured with hardware drivers, and the drivers included in the kernel layer can be at least one of the following drivers: audio driver, display driver, Bluetooth driver, camera driver, WIFI driver, USB driver, HDMI driver, sensor driver (such as fingerprint sensor, temperature sensor, pressure sensor, etc.), and power driver, etc.

[0077] In the context of review data analysis, the volume of review data for target products (such as the aforementioned display devices) is enormous. Manual analysis is labor-intensive, inefficient, and subject to subjective factors, resulting in low accuracy. Furthermore, this process requires significant human and material resources, resulting in high costs.

[0078] To address the above-mentioned issues, in some optional embodiments, a method for generating a demand analysis report is provided, which is applied to a server. The server may be a platform server corresponding to the display device 200. After the server generates the demand analysis report, it may send the demand analysis report to the display device 200 for display on the display device 200, allowing relevant personnel to view the demand analysis report on the display device 200. Of course, the server may also send the demand analysis report to the mobile terminal 300, allowing relevant personnel to view the demand analysis report on the mobile terminal 300 anytime and anywhere.

[0079] like Figure 5 The method for generating a demand analysis report includes:

[0080] S510: Obtain at least one review data for a target product from a data source.

[0081] The data source may include but is not limited to a review database of at least one e-commerce platform.

[0082] The target product can be any type and model of product and can be selected as needed. For example, the target product is a TV of brand A and model A1.

[0083] The review data may include buyers' comments on at least one dimension of the target product. For example, for a mobile phone, at least one dimension may include battery life, screen size, etc.

[0084] In practical scenarios, review text and metadata can also be extracted from review data. The metadata can include information such as the review ID (identification), the target product ID, the review, and a timestamp. The review text is standardized and cleaned, and the cleaned review text and metadata are encapsulated as a review data object. Each review data item corresponds to a review data object. Once at least one review data object corresponding to at least one review data item is obtained, it is used in subsequent steps.

[0085] The standardization cleaning process may include removing redundant spaces, removing characters other than emoticons, removing HTML (HyperText Markup Language) tags, normalizing the text (eg, converting full-width text to half-width text), and the like.

[0086] S520: Select a target agent for processing the comment data from at least one agent based on the comment data.

[0087] Exemplarily, the at least one intelligent agent mentioned above may include at least one of a sentiment analysis agent, a demand analysis agent, a problem identification agent, and a suggestion extraction agent. Of course, other intelligent agents may also be included, which is not limited here.

[0088] Among them, the function of the sentiment analysis agent is to identify the overall sentiment tendency of the comment data, which includes positive sentiment tendency and negative sentiment tendency.

[0089] Among them, the function of the demand analysis agent is to identify users' needs for the basic functions of the target product, clearly expressed expectations and preferences, and discover implicit but unexpressed needs from the review data.

[0090] Among them, the function of the problem identification agent is to identify various types of problems of the target product from the review data.

[0091] Among them, the function of the suggestion extraction agent is to extract improvement suggestions for the target product from the review data.

[0092] It is understandable that the number of target agents selected by the server for each comment data is one or more, and the target agents selected by the server for different comment data can be the same or different.

[0093] In actual scenarios, the server can select a corresponding target agent for each comment data from at least one agent through a coordinator.

[0094] S530: Input the comment data into the target agent to obtain comment analysis data of the comment data.

[0095] That is, after the server selects a target agent for a piece of comment data, it inputs the comment data into the corresponding target agent, and the target agent analyzes and processes the comment data to obtain corresponding comment analysis data.

[0096] Among them, the target intelligent agent can call the pre-trained language model, understand the comment text in the comment data through the pre-trained language model, and identify or extract relevant information according to the function of the target intelligent agent to obtain and output the comment analysis data.

[0097] Among them, each target intelligent agent can perform analysis tasks in parallel to improve processing efficiency.

[0098] For example, the target agents of a comment data include sentiment analysis agent, demand analysis agent, problem identification agent and suggestion extraction agent. Therefore, the comment analysis data that can be obtained for the comment data include: sentiment tendency, demand, problem and suggestion, thereby realizing multi-dimensional analysis of the comment data.

[0099] It is understandable that for each comment data, each target intelligent body will output corresponding comment analysis data. By summarizing the comment analysis data output by each target intelligent body corresponding to each comment data, the comment analysis data of the comment data can be obtained.

[0100] S 540 : Generate a demand analysis report for the target product based on the review analysis data corresponding to the at least one review data.

[0101] The demand analysis report can be understood as an analysis report generated by integrating and formatting the analysis data for at least one review of the target product. Furthermore, the demand analysis report includes information on user demand for the target product, providing structured recommendations for product development, marketing strategies, and customer service, helping to enhance data-driven decision-making capabilities for e-commerce sellers and manufacturers.

[0102] Among them, the demand analysis report can be a structured comprehensive analysis report.

[0103] It can be seen that in this embodiment, for each comment data, the server selects a target agent for processing the comment data from at least one agent based on the comment data, thereby improving the compatibility of the selected target agent with the comment data. In addition, since the number of target agents selected from at least one agent is not limited, the diversity of agents analyzing the comment data is further improved. Accordingly, the comment data is input into the corresponding diverse target agents to obtain corresponding comment analysis data, thereby improving the compatibility and diversity of the comment analysis data output by the target agent with the comment data, and further improving the accuracy and richness of the comment analysis data corresponding to the comment data. Accordingly, based on the comment analysis data corresponding to each comment data, a demand analysis report for the target product is generated, which can integrate different comment data for the target product from different agents, thereby improving the accuracy and richness of the content included in the demand analysis. Furthermore, since the demand analysis report can guide decisions such as product development, marketing strategies and customer service, it lays the foundation for optimizing and improving the product ecology of the target product. In addition, since the above process does not require manual analysis of the comment data, it not only improves the analysis efficiency, but also reduces the subjective bias caused by human analysis, improves the accuracy of the analysis results, and does not require a large amount of manpower and material resources, thereby reducing costs.

[0104] Based on the technical solutions of the above embodiments, an optional embodiment is also provided. In this optional embodiment, the step of selecting the target agent in S520 is refined.

[0105] See also Figure 6 , the steps for selecting the target agent include:

[0106] S610, based on the first strategy, select a target agent for processing comment data from at least one agent; and / or, based on the second strategy, select a target agent for processing comment data from at least one agent; wherein the first strategy is to select a target agent for processing comment data from at least one agent based on keywords in the comment data; the second strategy is to input the comment data into the selection agent to select a target agent for processing comment data from at least one agent.

[0107] Among them, the first strategy can be understood as a method of matching the corresponding target intelligent agent with the keywords in the comment data.

[0108] In an optional implementation, the keyword may be metadata in the review data, such as rating, length of the review data, source channel of the review data, etc.

[0109] For example, if the score is less than or equal to 2, it means that there is a high probability of negative issues in the review data. Therefore, the target agents determined by the first strategy include a problem recognition agent and a sentiment analysis agent.

[0110] In an optional implementation, the keywords may be words in the review text, for example, clear suggestive words such as hope, suggestion, next generation, etc.

[0111] Exemplarily, if the review text includes hopes, the target agents determined by the first strategy include a suggestion extraction agent and a demand analysis agent.

[0112] In an optional implementation, the keyword can be a logical combination of multiple words, and the logical combination supports AND, OR, NOT, etc.

[0113] Exemplarily, if the score is less than or equal to 3, and the review text includes "failure" or "broken", the target agents determined by the first strategy include a problem identification agent and a sentiment analysis agent.

[0114] It is understandable that the above three implementation methods can be arbitrarily combined as needed to form more first strategies.

[0115] Among them, for the second strategy, selecting an agent is a task scheduling model. The input of the selected agent is a comment data, and the output is a probability distribution vector, which represents the probability of the correlation between the comment data and each agent. Then, each probability value in the probability distribution vector is compared with the preset probability threshold. If the probability value is not lower than the preset probability threshold, the corresponding agent is used as the target agent.

[0116] The preset probability threshold can be set as needed, for example, 0.75. Of course, it can also be set to other values, which are not limited here.

[0117] Among them, the task scheduling model can be implemented using technologies such as FastText (fast text classification tool) and BERT (Bidirectional Encoder Representations from Transformers, a bidirectional encoder representation based on a self-attention mechanism neural network) distillation model.

[0118] For example, the comment data "I feel that the battery life of this mobile phone can only last for half a day. If you go out for a trip, you have to bring a power bank, which is a bit troublesome" is input into the selection agent. The selection agent can identify the user's dissatisfaction with "battery life" through deep semantic understanding. The output probability distribution vector is (0.5, 0.9, 0.6 and 0.5), where the probability value 0.9 corresponds to the demand analysis agent, and 0.6 corresponds to the problem identification agent. The preset probability threshold is 0.6, so the demand analysis agent and the problem identification agent are used as target agents.

[0119] As can be seen, in this embodiment, the target agent can be selected based on the first strategy, or based on the second strategy. Alternatively, the target agent can be selected based on both the first and second strategies, with the union of the target agent selected based on the first strategy and the target agent selected based on the second strategy being the final target agent. In other words, the first strategy and / or the second strategy are used to select a corresponding target agent for each piece of review data, ensuring that the target agent is compatible with the review data, and the strategies employed are flexible and diverse.

[0120] Based on the technical solutions of the above embodiments, an optional embodiment is also provided. In this optional embodiment, the step of selecting the target agent in S520 is refined.

[0121] See also Figure 7 , the steps for selecting the target agent include:

[0122] S710, selecting a target strategy from the first strategy and the second strategy, and selecting a target agent for processing comment data from at least one agent based on the target strategy.

[0123] That is, the server selects one strategy from the first strategy and the second strategy as the target strategy, and selects a corresponding target agent for the comment data based on the target strategy.

[0124] There are many ways to select the target strategy. For example, based on the degree of match between the review data and the first strategy and the second strategy, the strategy with the higher match is selected as the target strategy. Of course, other methods can also be selected and are not limited here.

[0125] It can be seen that this embodiment selects the target strategy from the first strategy and the second strategy, thereby improving the adaptability of the target intelligent agent and the comment data, and further improving the rationality of the demand analysis report.

[0126] Based on the technical solution of the previous embodiment, an optional embodiment is provided. In this optional embodiment, the target policy selection step in S710 is refined. The target policy selection step includes at least one of the following:

[0127] (1) Selecting a target strategy from the first strategy and the second strategy based on the importance data of the keywords in the review data;

[0128] (2) According to the system load of the server, a target strategy is selected from the first strategy and the second strategy.

[0129] For example, for the above (1), if the importance of the keyword is high, the first strategy can be used as the target strategy. If the importance of the keyword is low, the second strategy can be used as the target strategy. The reason is that the more important the keyword is, the more compatible the target agent selected by keyword matching is with the comment data. The importance data of the keyword can be compared with a preset threshold to determine the importance of the keyword.

[0130] For example, with respect to the above (2), if the system load of the server is low and the server currently has sufficient system resources available, the second strategy is used as the target strategy, thereby improving the efficiency of selecting the target agent. If the system load of the server is high (for example, the server performs the demand analysis report generation task for multiple products), the server does not have sufficient system resources available, and the first strategy is used as the target strategy. The reason is that compared with the use of keywords, the use of the selection agent requires more system resources in the process of selecting the target agent. Therefore, when the system resources are insufficient, the use of the first strategy as the target strategy can reduce the occupation of system resources, thereby ensuring the smooth execution of the demand analysis report generation task.

[0131] It can be seen that in this embodiment, the target strategy is selected from the first strategy and the second strategy based on the importance data of the keywords in the comment data and / or the system load of the server, which can ensure the adaptability of the selected target intelligent agent to the comment data and ensure the smooth execution of the demand analysis report generation task.

[0132] Based on the technical solution of the previous embodiment, an optional embodiment is also provided. In this optional embodiment, the steps for determining the keyword importance data are refined. The steps for determining the keyword importance data include:

[0133] 1. Get the length ratio of keywords in the comment data.

[0134] It is understandable that the longer the length of a keyword in the comment data is, the more important the keyword is. Therefore, the length of the keyword in the comment data is taken into consideration when calculating the importance of the keyword.

[0135] 2. Determine the lexical distribution of words with the same semantics in the keywords.

[0136] Among them, a comment data includes multiple keywords, and there are words with the same semantics in each keyword. The proportion of the number of words with the same semantics is used to determine the vocabulary distribution of words with the same semantics.

[0137] For example, a comment data includes 10 keywords, of which 5 keywords are the same semantic vocabulary A, 3 keywords are the same semantic vocabulary B, and 2 keywords are the same semantic vocabulary C. Therefore, the vocabulary distribution of the same semantic vocabulary A is 50%, the vocabulary distribution of the same semantic vocabulary B is 30%, and the vocabulary distribution of the same semantic vocabulary C is 20%.

[0138] It is understandable that the higher the proportion of words with the same semantics, the higher the corresponding importance. Therefore, the vocabulary distribution of words with the same semantics is considered when determining the importance data of keywords.

[0139] 3. Determine the vocabulary ratio of preset important category keywords in the keywords.

[0140] It is understandable that there are many types of keywords, and some types of keywords are more important, so they can be set as preset important category keywords, and the vocabulary proportion of the preset important category keywords can be considered when calculating the keyword importance data.

[0141] 4. Determine the importance data of the keyword based on at least one of the length ratio, vocabulary distribution, and vocabulary ratio.

[0142] It can be seen that the importance data of keywords can be determined based on the above-mentioned length ratio, the above-mentioned vocabulary distribution, the above-mentioned vocabulary ratio, or a combination of at least two of the above. Based on at least one of the length ratio, vocabulary distribution, and vocabulary ratio, the importance of keywords can be determined, thereby accurately determining the importance data, which in turn helps to select an adaptive target strategy.

[0143] Based on the technical solutions of the above embodiments, an optional embodiment is provided. In this optional embodiment, the step of generating the demand analysis report in S540 is refined.

[0144] See also Figure 8 , the steps for generating a demand analysis report include:

[0145] S810, for the same comment data, determine to correct the comment analysis data corresponding to the comment data according to the priority of the target intelligent body corresponding to the comment data and / or the analysis consistency of the comment analysis data corresponding to the comment data.

[0146] In an optional implementation, different agents are prioritized in advance, with agents that identify and extract objective facts taking precedence over agents that identify subjective feelings. For example, a question recognition agent may take precedence over a sentiment analysis agent.

[0147] For example, the comment data is: "The logistics is very fast, great! But the phone couldn't turn on the next day." The sentiment analysis agent may make a misjudgment and output a positive sentiment tendency, but the problem recognition agent identifies the fatal problem of not being able to turn on the phone the next day. Therefore, the comment analysis data of the problem recognition agent is used to correct the comment analysis data of the sentiment analysis agent and correct it to a negative one.

[0148] It can be seen that this method can be used to correct some situations where the content is praised but actually criticized, thus ensuring the accuracy of the subsequent demand analysis report.

[0149] In an optional embodiment, a consistency judgment standard is preset. For example, when the review analysis data of each target agent are inconsistent, the consistency judgment standard is to use the majority review analysis data to correct the minority review analysis data.

[0150] For example, for the five target intelligent entities of a comment data, the comment analysis data of four target intelligent entities are negative content, and the comment analysis data of one target intelligent entity is positive content. Therefore, the negative comment analysis data of the four target intelligent entities are used to correct the positive comment analysis data of the one target intelligent entity.

[0151] S820: Generate a demand analysis report for the target product based on the revised review analysis data corresponding to the at least one review data.

[0152] It can be seen that when there are contradictions in the comment analysis data of each target intelligent agent, the comment analysis data output by the target intelligent agent with a relatively low priority or a small number of comment analysis data are corrected to eliminate the contradictions and ensure the accuracy of the demand analysis report.

[0153] Based on the technical solutions of the above embodiments, an optional embodiment is also provided. In this optional embodiment, the review analysis data is refined to include evaluation entities and evaluation feelings corresponding to the evaluation entities, and the generation steps of the demand analysis report in S820 are refined.

[0154] See also Figure 9 , the steps for generating a demand analysis report include:

[0155] S910: Group the corrected review analysis data to obtain review analysis data groups corresponding to different evaluation feeling dimensions under the same evaluation entity dimension.

[0156] Among them, the evaluation entity can be understood as the product elements or service elements corresponding to the target product.

[0157] Exemplarily, the evaluation entity may be a battery, a camera, or other product elements, or may be logistics, pre-sales customer service, after-sales service, or other service elements.

[0158] Among them, evaluation feelings are the emotional tendencies mentioned above. Evaluation feelings include positive evaluation feelings and negative evaluation feelings.

[0159] It can be understood that the revised review analysis data corresponding to each review data about the target product are grouped, and each evaluation feeling under each evaluation entity dimension corresponds to a review analysis data group, that is, the review analysis data in a review analysis data group are review analysis data for the same evaluation entity and corresponding to the same evaluation feeling.

[0160] For example, for the evaluation entity of headphones, a comment analysis data in the comment analysis data group includes: the evaluation feeling is negative; the problem: uncomfortable to wear; the demand: improve wearing comfort; the suggestion: use softer earmuff material.

[0161] S920, according to the preset template, the comment analysis data in the comment analysis data group is input into the arbitration intelligent agent to obtain the target evaluation analysis data under the evaluation entity dimension and evaluation feeling dimension corresponding to the comment analysis data group.

[0162] The preset template may be a causal relationship template, for example, a template in which a problem is a cause and an emotion is an effect, or a template in which a problem is a cause and a need or suggestion is an effect.

[0163] For example, for positive evaluation feelings, the arbitration agent can sort out the reasons leading to the positive evaluation feelings from the comment analysis data group, thereby forming the cause-positive evaluation feeling target evaluation analysis data.

[0164] For example, for negative evaluation feelings, the arbitration agent can sort out the problems that lead to negative evaluation feelings from the comment analysis data group, extract the user's needs generated by this, and put forward suggestions for improvement, thereby forming target evaluation analysis data of problems - negative evaluation feelings - needs and suggestions.

[0165] S930: Generate a demand analysis report for the target product based on the target evaluation analysis data under different evaluation entity dimensions and evaluation feeling dimensions.

[0166] It can be seen that the revised review analysis data are grouped based on the evaluation entity and evaluation feeling, and each review analysis data group is then input into the arbitration agent. Based on the above-mentioned causal relationship template, the arbitration agent can sort out the causal relationship in the review analysis data group and obtain the target evaluation analysis data with causal relationship, which is helpful to generate a demand analysis report with a logical chain.

[0167] Based on the technical solution of the previous embodiment, an optional embodiment is provided. In this optional embodiment, the steps for obtaining the target evaluation analysis data are refined.

[0168] See also Figure 10 ,The steps for obtaining target evaluation and analysis data include:

[0169] S1010, for the comment analysis data group under the negative evaluation feeling dimension of the same evaluation entity dimension, the evaluation analysis data group is input into the arbitration intelligent agent to obtain reference evaluation analysis data generated according to the preset template.

[0170] S1020, obtaining reference evaluation analysis data of existing problem demand data and problem suggestion data matching the problem demand data as target evaluation analysis data under the corresponding evaluation entity dimension and negative evaluation feeling dimension of the comment analysis data group.

[0171] Among them, problem demand data refers to the demand generated by the problem, and problem suggestion data refers to the suggestion generated by the problem.

[0172] For example, a requirement in a reference evaluation analysis data is: improve wearing comfort, and a suggestion is: use a softer earmuff material. The requirement and the suggestion match.

[0173] For example, a requirement in a reference evaluation analysis data is: to improve wearing comfort, and the suggestion is: to use a battery with longer battery life. The requirement and the suggestion do not match.

[0174] As can be seen, in this embodiment, a review analysis data set with negative evaluations of the same evaluation entity is input into the arbitration agent. The results output by the arbitration agent are first used as reference evaluation analysis data, and then a judgment is made as to whether the requirements and suggestions in the reference evaluation analysis data match. If the requirements and suggestions do not match, the corresponding reference evaluation analysis data cannot be used as the target evaluation analysis data. If the requirements and suggestions do match, the corresponding reference evaluation analysis data is used as the target evaluation analysis data. In this way, the target evaluation analysis data can be ensured to be logical, avoiding the appearance of unreasonable content in the demand analysis report.

[0175] It is understandable that a review analysis data set for the same evaluation entity with positive evaluation feelings is input into the arbitration agent, and the result output by the arbitration agent can be directly used as the target evaluation analysis data.

[0176] Based on the technical solution of the previous embodiment, an optional embodiment is provided. In this optional embodiment, the step of generating the demand analysis report in S930 is refined.

[0177] See also Figure 11 , the steps for generating a demand analysis report include:

[0178] S1110 , for the reference evaluation analysis data under the same evaluation entity dimension, obtain the demand proportions of different problem demand data as the demand confidence of the corresponding problem demand data under the evaluation entity dimension.

[0179] Among them, the problem demand data is the demand.

[0180] It is understandable that there may be multiple requirements for the same evaluation entity. For example, for a mobile phone screen, the requirements may include screen size requirements, screen resolution requirements, etc.

[0181] In an optional implementation, for each requirement of each evaluation entity, a first quantity corresponding to the corresponding reference evaluation analysis data is determined, and a second quantity corresponding to the reference evaluation analysis data that matches the requirement and the suggestion is determined, and the ratio of the second quantity to the first quantity is used as the corresponding requirement ratio.

[0182] For example, for the screen size requirements for mobile phones, there are 100 reference evaluation analysis data. Of these, 30 requirements and recommendations do not match, while the remaining 70 requirements and recommendations match, accounting for 70% of the requirements. Therefore, the confidence level for the screen size requirements for mobile phones is 70%.

[0183] S1120 , sorting the target evaluation analysis data according to the demand confidence of different problem demand data under the same evaluation entity dimension, and generating a demand analysis report for the target product according to the sorting result.

[0184] Among them, for the same evaluation entity, the higher the demand confidence, the higher the target evaluation analysis data of the corresponding demand will be in the demand analysis report.

[0185] It can be seen that in the process of generating a demand analysis report, it is necessary to sort the target evaluation analysis data corresponding to each demand of the same evaluation entity, so as to realize the typesetting of the target evaluation analysis data and thus improve the readability of the demand analysis report.

[0186] In actual scenarios, it is also possible to perform statistical analysis on the target evaluation analysis data. For example, statistics can be collected on the distribution of each evaluation feeling for each evaluation entity, the top N requirements of each evaluation entity, etc., where N is an integer greater than or equal to 1. Based on the statistical data, an overview of the demand analysis report is formed. The statistical data can also be formed into charts, such as sentiment distribution pie charts, demand word clouds, and problem trend charts. In addition to the overview and charts formed by the statistical data, the main content of the demand analysis report is the detailed analysis content formed by the target evaluation analysis data of each evaluation feeling under each entity dimension in a preset order.

[0187] Based on the technical solutions of the above embodiments, an optional embodiment is also provided. In this optional embodiment, a specific process of a method for generating a demand analysis report is provided.

[0188] See also Figure 12 , the method for generating demand analysis report includes:

[0189] S1210: The server obtains at least one review data for the target product from a data source.

[0190] S1220, the system load of the server is relatively high, and a target intelligent agent is selected from at least one intelligent agent for each comment data based on the first strategy, and the comment data is input into the corresponding target intelligent agent to obtain corresponding comment analysis data.

[0191] S1230, the server determines to correct the comment analysis data corresponding to the same comment data according to the priority of the target intelligent body corresponding to the comment data and / or the analysis consistency of the comment analysis data corresponding to the comment data.

[0192] S1240: The server groups the corrected review analysis data to obtain review analysis data groups corresponding to different evaluation feeling dimensions under the same evaluation entity dimension.

[0193] S1250, the server inputs the review analysis data group under the negative evaluation feeling dimension of the same evaluation entity dimension into the arbitration intelligent agent to obtain reference evaluation analysis data generated according to the preset template.

[0194] S1260, the server obtains reference evaluation analysis data of existing problem demand data and problem suggestion data matching the problem demand data as target evaluation analysis data under the corresponding evaluation entity dimension and negative evaluation feeling dimension of the comment analysis data group.

[0195] S1270, the server analyzes the reference evaluation data under the same evaluation entity dimension, and obtains the demand proportions of different problem demand data as the demand confidence of the corresponding problem demand data under the evaluation entity dimension.

[0196] S1280, the server sorts the target evaluation analysis data according to the demand confidence of different problem demand data under the same evaluation entity dimension, and generates a demand analysis report for the target product according to the sorting result.

[0197] S1290, the server sends the demand analysis report to the display device, thereby realizing visualization of the demand analysis report.

[0198] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0199] Based on the same inventive concept, in some embodiments, a demand analysis report generation device for implementing the aforementioned demand analysis report generation method is also provided. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more demand analysis report generation device embodiments provided below can be found in the above-mentioned limitations of the demand analysis report generation method and will not be repeated here.

[0200] In an exemplary embodiment, Figure 13As shown, a demand analysis report generation device is provided, including: a data acquisition module 1310, a target determination module 1320, a data input module 1330 and a report generation module 1340, wherein:

[0201] The data acquisition module 1310 is configured to acquire at least one review data for a target product from the data source;

[0202] A target determination module 1320 is configured to select a target agent for processing the review data from at least one agent based on the review data;

[0203] A data input module 1330 is configured to input the comment data into the target agent to obtain comment analysis data of the comment data;

[0204] The report generating module 1340 is configured to generate a demand analysis report for the target product based on the review analysis data corresponding to the at least one review data.

[0205] In one embodiment, the target determination module includes at least one of the following units:

[0206] A first selection unit is configured to select a target agent for processing the review data from at least one agent based on a first strategy;

[0207] A second selection unit is configured to select a target agent for processing the review data from at least one agent based on a second strategy;

[0208] Among them, the first strategy is to select a target intelligent agent for processing the comment data from at least one intelligent agent based on the keywords in the comment data; the second strategy is to input the comment data into the selection intelligent agent to select a target intelligent agent for processing the comment data from at least one intelligent agent.

[0209] In one embodiment, the target determination module further includes:

[0210] The third selection unit is used to select a target strategy from the first strategy and the second strategy, and select a target agent for processing the comment data from at least one agent based on the target strategy.

[0211] In one embodiment, the third selection unit is specifically used to: select a target strategy from the first strategy and the second strategy based on the importance data of the keywords in the comment data; select a target strategy from the first strategy and the second strategy based on the system load of the server.

[0212] In one embodiment, the apparatus further comprises:

[0213] An importance determination module is used to obtain the length ratio of keywords in the comment data; determine the vocabulary distribution of the same semantic words in the keywords; determine the vocabulary ratio of preset important category keywords in the keywords; and determine the importance data of the keywords based on at least one of the length ratio, vocabulary distribution and vocabulary ratio.

[0214] In one embodiment, the report generation module includes:

[0215] a data correction unit, configured to determine, for the same review data, to correct the review analysis data corresponding to the review data according to the priority of the target intelligent agent corresponding to the review data and / or the analysis consistency of the review analysis data corresponding to the review data;

[0216] A report generating unit is configured to generate a demand analysis report for the target product based on the revised review analysis data corresponding to the at least one review data.

[0217] In one embodiment, the review analysis data includes evaluation entities and evaluation feelings corresponding to the evaluation entities; accordingly, the report generation unit includes:

[0218] The grouping subunit is used to group the corrected review analysis data to obtain review analysis data groups corresponding to different evaluation feeling dimensions under the same evaluation entity dimension;

[0219] A target determination subunit is used to input the review analysis data in the review analysis data group into the arbitration agent according to a preset template, and obtain target evaluation analysis data under the evaluation entity dimension and evaluation feeling dimension corresponding to the review analysis data group;

[0220] The report generation subunit is used to generate a demand analysis report for the target product based on the target evaluation analysis data under different evaluation entity dimensions and evaluation feeling dimensions.

[0221] In one embodiment, the target determination subunit is specifically used to: for a comment analysis data group with the same evaluation entity dimension under the negative evaluation feeling dimension, input the evaluation analysis data group into the arbitration intelligent agent to obtain reference evaluation analysis data generated according to a preset template; obtain reference evaluation analysis data of existing problem demand data and problem suggestion data matching the problem demand data as target evaluation analysis data under the evaluation entity dimension and negative evaluation feeling dimension corresponding to the comment analysis data group.

[0222] In one embodiment, the report generation sub-unit is specifically used to: for the reference evaluation analysis data under the same evaluation entity dimension, obtain the demand ratio of different problem demand data as the demand confidence of the corresponding problem demand data under the evaluation entity dimension; sort the target evaluation analysis data according to the demand confidence of different problem demand data under the same evaluation entity dimension, and generate a demand analysis report for the target product based on the sorting results.

[0223] In some optional embodiments, a server is provided, whose internal structure diagram can be as follows: Figure 14 As shown. The server includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the server is used to provide computing and control capabilities. The memory of the server includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the server is used to store relevant data. The input / output interface of the server is used to exchange information between the processor and an external device. The communication interface of the server is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a content recommendation method is implemented.

[0224] Those skilled in the art will understand that Figure 14 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the server to which the solution of the present application is applied. The specific server may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0225] In some optional embodiments, a server is provided, comprising: a communication device configured to communicate with a data source; and at least one processor connected to the communication device and configured to execute the steps in the above method embodiments.

[0226] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0227] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0228] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0229] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile memory and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a programmable logic unit (PLC), a data processing logic unit based on quantum computing, an artificial intelligence (AI) processor, and the like.

[0230] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0231] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A server, characterized in that: include: a communication device configured to communicate with a data source; at least one processor, connected to the communication device and configured to: Obtain at least one review data for a target product from the data source; selecting, based on the comment data, a target agent for processing the comment data from at least one agent; Inputting the comment data into the target agent to obtain comment analysis data of the comment data; A demand analysis report for the target product is generated based on the review analysis data corresponding to the at least one piece of review data.

2. The server according to claim 1, wherein: When executing the step of selecting, from at least one agent, a target agent for processing the comment data based on the comment data, the processor is configured to perform at least one of the following: Based on a first strategy, selecting a target agent for processing the review data from at least one agent; Based on the second strategy, selecting a target agent for processing the review data from at least one agent; Among them, the first strategy is to select a target intelligent agent for processing the comment data from at least one intelligent agent based on the keywords in the comment data; the second strategy is to input the comment data into the selection intelligent agent to select a target intelligent agent for processing the comment data from at least one intelligent agent.

3. The server according to claim 2, wherein: When executing the step of selecting, from at least one agent, a target agent for processing the comment data according to the comment data, the processor is further configured to: A target strategy is selected from the first strategy and the second strategy, and a target agent for processing the comment data is selected from at least one agent based on the target strategy.

4. The server according to claim 3, wherein: The processor, when processing the selecting of the target policy from the first policy and the second policy, is configured to perform at least one of the following: Selecting a target strategy from the first strategy and the second strategy according to the importance data of the keywords in the review data; A target policy is selected from the first policy and the second policy according to the system load of the server.

5. The server according to claim 4, wherein: The processor is further configured to: Obtaining a length ratio of keywords in the comment data; Determining the vocabulary distribution of words with the same semantic meaning in the keywords; Determine the vocabulary ratio of preset important category keywords in the keywords; The importance data of the keyword is determined based on at least one of the length ratio, vocabulary distribution and vocabulary ratio.

6. The server according to any one of claims 1 to 5, characterized in that: When executing the review analysis data corresponding to the at least one review data to generate a demand analysis report for the target product, the processor is configured to: For the same review data, determining to modify the review analysis data corresponding to the review data according to the priority of the target intelligent agent corresponding to the review data and / or the analysis consistency of the review analysis data corresponding to the review data; A demand analysis report for the target product is generated based on the revised review analysis data corresponding to the at least one review data.

7. The server according to claim 6, wherein: The review analysis data includes an evaluation entity and the evaluation experience corresponding to the evaluation entity; accordingly, the processor generates a demand analysis report for the target product by executing the review analysis data corrected according to the at least one review data, including: The revised review analysis data is grouped to obtain review analysis data groups corresponding to different evaluation feeling dimensions under the same evaluation entity dimension; According to a preset template, the review analysis data in the review analysis data group is input into the arbitration agent to obtain the target evaluation analysis data under the evaluation entity dimension and the evaluation feeling dimension corresponding to the review analysis data group; Based on the target evaluation analysis data under different evaluation entity dimensions and evaluation feeling dimensions, a demand analysis report for the target product is generated.

8. The server according to claim 7, wherein: When the processor executes the step of inputting the review analysis data in the review analysis data group into the arbitration agent according to the preset template and obtaining the target review analysis data corresponding to the evaluation entity dimension and the evaluation feeling dimension of the review analysis data group, the processor is configured to: For a review analysis data set under a negative evaluation perception dimension for the same evaluation entity dimension, the review analysis data set is input into an arbitration agent to obtain reference review analysis data generated according to a preset template; Reference evaluation analysis data of existing problem demand data and problem suggestion data matching the problem demand data are obtained as target evaluation analysis data under the corresponding evaluation entity dimension and negative evaluation feeling dimension of the comment analysis data group.

9. The server according to claim 8, wherein: When executing the target evaluation analysis data under different evaluation entity dimensions and evaluation perception dimensions to generate a demand analysis report for the target product, the processor is configured to: For the reference evaluation analysis data under the same evaluation entity dimension, the demand ratio of different problem demand data is obtained as the demand confidence of the corresponding problem demand data under the evaluation entity dimension; The target evaluation analysis data are sorted according to the demand confidence of different problem demand data under the same evaluation entity dimension, and a demand analysis report for the target product is generated according to the sorting result.

10. A method for generating a demand analysis report, characterized in that: include: Obtain at least one review data for the target product from the data source; selecting, based on the comment data, a target agent for processing the comment data from at least one agent; Inputting the comment data into the target agent to obtain comment analysis data of the comment data; A demand analysis report for the target product is generated based on the review analysis data corresponding to the at least one piece of review data.

Images