CN116737906A

CN116737906A - Information display method, device, electronic equipment and storage medium

Info

Publication number: CN116737906A
Application number: CN202310807445.XA
Authority: CN
Inventors: 袁洁
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-07-03
Filing date: 2023-07-03
Publication date: 2023-09-12

Abstract

The disclosure provides an information display method, relates to the technical field of artificial intelligence, and particularly relates to the technical fields of man-machine interaction, intelligent question-answering, natural language processing, large language models and generated dialogue models. The specific implementation scheme is as follows: in response to receiving input information from a target object, determining a target question for the target entity from the input information; according to the target problem, basic data of a target entity and reference data of a category to which the target entity belongs are obtained; generating response information of the target problem according to the basic data and the reference data; and displaying the response information. The disclosure also provides an information display device, an electronic device and a storage medium.

Description

Information display method, device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly to the field of man-machine interaction, intelligent question-answering, natural language processing, large language models, and generative dialog models. More particularly, the present disclosure provides an information display method, an apparatus, an electronic device, and a storage medium.

Background

With the continuous development and maturity of artificial intelligence technology, intelligent dialogue robots (such as customer service robots) are gradually sharing some services of traditional artificial customer service, and can rapidly and efficiently solve the problem of target objects.

Disclosure of Invention

The disclosure provides an information display method, an information display device, information display equipment and a storage medium.

According to a first aspect, there is provided an information presentation method comprising: in response to receiving input information from a target object, determining a target question for the target entity from the input information; according to the target problem, basic data of a target entity and reference data of a category to which the target entity belongs are obtained; generating response information of the target problem according to the basic data and the reference data; and displaying the response information.

According to a second aspect, there is provided an information presentation apparatus comprising: a question determination module for determining a target question for a target entity from input information in response to receiving the input information from the target object; the first data acquisition module is used for acquiring basic data of a target entity and reference data of a category to which the target entity belongs according to the target problem; the response information generation module is used for generating response information of the target problem according to the basic data and the reference data; and the display module is used for displaying the response information.

According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method provided in accordance with the present disclosure.

According to a fourth aspect, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform a method provided according to the present disclosure.

According to a fifth aspect, there is provided a computer program product comprising a computer program stored on at least one of a readable storage medium and an electronic device, which, when executed by a processor, implements a method provided according to the present disclosure.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1A is a schematic diagram showing information of a customer service product in the related art;

FIG. 1B is a scene graph to which information presentation methods and apparatus may be applied according to one embodiment of the present disclosure;

FIG. 2 is a flow chart of an information presentation method according to one embodiment of the present disclosure;

FIG. 3 is a system architecture diagram of an information presentation method according to one embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a method of generating a dialog flow according to one embodiment of the disclosure;

FIG. 5 is a block diagram of an information presentation apparatus according to one embodiment of the present disclosure;

fig. 6 is a block diagram of an electronic device of an information presentation method according to one embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the scenario of providing services to an enterprise, in the face of target questions posed by users of the enterprise, a databased customer service product may be generated to provide customer service to the users. For example, the target problems of the user include poor product management effect, basic data (such as exposure, click rate, etc.) of the product of the user can be obtained, and a signboard tool such as a trend chart is generated based on the basic data, so as to help the user analyze the operation condition and improve the operation effect.

Fig. 1A is a schematic diagram showing information of a customer service product in the related art.

As shown in fig. 1A, the customer service product may be a databased signage tool for an electronic store operated by a user. For example, a user may operate an electronic store on an electronic platform, where the electronic store may be associated with at least one item, which may include physical items such as clothing, and may also include electronic items such as resources. The target problem for the user may be a desire to promote the business effect of the electronic store, etc.

Aiming at the target problem of the user, the business effect data of the electronic store can be obtained, and the business effect data are analyzed and displayed in the form of trend graphs and the like.

As shown in fig. 1A, the billboard tool 110 includes a display area 111 and a display area 112. The presentation area 111 presents data overview controls, flow analysis controls, item analysis controls, and the like. The presentation area 112 may be a specific content of the data overview displayed in response to a target object (e.g., a user) clicking on the data overview control.

The display area 112 displays some core data of the electronic store operated by the user, such as exposure (may include exposure of the electronic store and exposure of the item), click-through (may include click-through of the electronic store and click-through of the item), visit capacity, phone volume, and the like.

The display area 112 also displays trend graphs generated based on these core data, such as exposure, click-through, phone-call volume decreasing in order, the conversion of exposure or click-through to item sales (click conversion) being 0.00%.

The flow analysis control and the item analysis control can also display specific flow analysis content and item analysis content in response to the user clicking on the flow analysis control.

The problem existing in the operation of the electronic store by the user, such as higher exposure, but too low conversion rate, which may be that the image-text description information of the articles in the electronic store is unattractive, etc., can be analyzed through the signboard tool, so that the user can be helped to take corresponding measures to improve the conversion rate, and further the operation effect is improved.

However, the sign tool needs to learn more index meanings for users, and needs to have a certain mathematical ability to analyze. For users with low familiarity degree of the internet, the learning and using cost is extremely high, and the process is complex. The user may also select a surrogate service, analyze it by a professional customer service of the facilitator using a data tool, and then provide an optimization scheme or suggestion to the user based on the analysis result. However, the cost of the substitution operation service is high, meanwhile, the culture cost exists for professional customer service of a service provider, and the customer service is used as a position with higher mobility, so that the problems of unskilled service and loss of users caused by unsmooth handover are easy to occur.

Accordingly, the customer service products in the form of signage data tools are generally inadequate in service capacity. There is an urgent need for a customer service product that is more efficient, more effective and less costly to address the problem for the user.

Fig. 1B is a scene diagram to which information presentation methods and apparatuses may be applied according to one embodiment of the present disclosure.

As shown in fig. 1B, the scenario 120 of the present embodiment may be a presentation interface of a customer service product provided by the present disclosure, which is presented in a form of multiple rounds of conversations with a user. The presentation page may be presented on a screen of an electronic device, which may include a smart phone, a tablet, a laptop, a desktop computer, and the like.

For example, the user inputs "i feel my store operating poorly, help me see what is? By the aid of the client service product display response message of 'you good', you can specifically describe your questions and difficulties, and I can provide more accurate help for you. ". The user further enters questions (e.g., low conversion rate) and the customer service product presents new response information (e.g., may consider offering offers). Depending on the user feedback (e.g., not wanting to lower the price), more response information (e.g., optimizing the item's graphic description information) may also be presented.

Compared with a signboard tool which needs a user to understand more indexes, the method solves the problem for the user in a multi-turn dialogue mode, reduces the use cost of the user, enables the problem and the solution of the user to be gradually clear through multi-turn dialogue interaction, achieves effective communication with the user, and enables the problem of the user to be effectively solved.

In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.

In the technical scheme of the disclosure, the authorization or consent of the user is obtained before the personal information of the user is obtained or acquired.

Fig. 2 is a flow chart of an information presentation method according to one embodiment of the present disclosure.

As shown in fig. 2, the information presentation method 200 includes operations S210 to S240.

In response to receiving input information from the target object, a target question for the target entity is determined from the input information in operation S210.

For example, the target object may be an enterprise user, in particular a merchant operating an electronic store on an electronic platform. The target entity may refer to the electronic store. The target object may input information to the electronic device in the form of voice or text, and the input information may be presented on a screen of the electronic device in the form of natural language. For example, the input information of the user includes "i feel bad in the business of my store, what is i'm looking at? ".

The electronic device receives input information of a user, and can extract target questions of the user from the input information, wherein the target questions are aimed at target entities. For example, the target problem is "the business effect of the target entity is bad" or "the business effect of the target entity is desired to be better".

The input information of the user can be converted into natural language, the natural language is input into a natural language processing model, and the target problem is extracted from the natural language processing model. The natural language processing model may be a pre-trained large language model with natural language understanding capabilities, which may be a generative dialog model that may generate response information for a user's target questions to enable multiple rounds of dialog with the user.

In operation S220, according to the target problem, basic data of the target entity and reference data of a category to which the target entity belongs are obtained.

For example, the underlying data of the target entity may include business activity data of the target object for the target entity (e.g., update frequency of items, response buyer rates, etc.), business status data of the target entity (e.g., brand authorization information, qualification information, etc. of the target entity), and business effect data of the target entity (e.g., exposure of the target entity or product, click-through amount of product, conversion rate of click-through amount to item sales, etc.).

The category to which the target entity belongs may be industry information of the target entity, which may be determined based on the item information uploaded by the user, or industry information filed by the user.

The benchmark data may be determined based on the base data of each of a plurality of entities belonging to the same category (or industry). For example, for each category, the average of the base data of all entities belonging to that category may be taken as the base data for that category. For example, for each category, all entities belonging to the category may also be divided into a plurality of (e.g., 3) levels by a certain dimension (e.g., item sales), and for each level, the level reference data is determined from the base data of the entity set of that level.

For a target entity, reference data of a category to which the target entity belongs can be acquired, and the reference data can represent the average level of industries to which the target entity belongs. Or obtaining basic data of the target grade in the industry of the target entity, wherein the target grade is the grade of the target entity. Benchmark data may include business activity benchmark data (e.g., industry average frequency of updates to items, customer query panel response rates), and business effect benchmark data (e.g., industry average exposure to entities, product exposure, product click throughs, click conversions, etc.).

In operation S230, response information of the target question is generated based on the base data and the reference data.

For example, the basic data is actual business data of the target entity, and the reference data is an average level of business data of industries to which the target entity belongs. Thus, a gap between the target entity and industry average may be determined based on the base data and the benchmark data, which may include a gap in business activity (e.g., frequency of item updates, response buyer rates), and business effect benchmark data (e.g., entity exposure, product clicks, click conversions, etc.). According to the gap between the target entity and the industry average level, a target strategy aiming at the gap can be determined so as to improve the operation effect of the target entity.

For example, the target policy may include a policy for the update frequency of items, a policy for the offer of items, and so on.

After generating the target policy, the target policy may be converted into natural language description information as response information. For example, the answer message is "suggest you some preferential activity".

In operation S240, response information is presented.

For example, the response information in the form of natural language may be displayed on the screen of the electronic device, or the response information may also be played in the form of voice, or the response information may also be displayed on the screen of the electronic device at the same time, and played.

The embodiment of the disclosure receives input information of a user, extracts a target problem from the input information, acquires basic data and reference data of a target entity, determines response information according to the basic data and the reference data, and displays the response information. According to the embodiment, customer service can be provided for the user in a multi-round dialogue mode, learning and understanding cost of the user is greatly reduced, effective communication is achieved through the multi-round dialogue in a very friendly and intimate mode, the target problem is gradually solved, communication efficiency is higher, and problem solving is more convenient.

In addition, compared with a mode of professional customer service operation, the method and the device can greatly reduce the labor cost of professional customer service training and risks such as misunderstanding, information loss and the like caused by handover.

In addition, for the electronic platform using the information display method provided by the embodiment, the embodiment can improve the trust feeling and viscosity of the user for the platform.

According to an embodiment of the present disclosure, operation S230 includes determining at least one candidate policy from the base data and the reference data; determining a target policy from the at least one candidate policy; and generating natural language description information of the target strategy as response information.

For example, if the update frequency of the target object for items associated with the target entity is below an industry average level, candidate policies for the update frequency of the items may be generated. For another example, if the conversion rate of the target entity is below an industry average level, a candidate policy for the offer for the item may be generated.

In the case of generating a plurality of candidate policies, a target policy may be determined from the plurality of candidate policies according to weights of the respective candidate policies. The weight of each candidate policy may be preset and updated according to feedback information of the user. For example, the initial weight of each candidate strategy is the same, and one candidate strategy is randomly selected from a plurality of candidate strategies to serve as a target strategy. After receiving the feedback information of the user for the target policy, the weight of the target policy may be adjusted.

For example, the feedback information may characterize a positive or negative emotion of the user for the target policy. If the user feedback 'the operation effect is improved' after the user adopts the target strategy, the positive emotion of the feedback information representing the user can be determined, and the weight of the target strategy can be improved. If the user feedback 'operation effect is not improved' after the user adopts the target strategy, the feedback information can be determined to represent the negative emotion of the user, and the weight of the target strategy can be reduced.

According to an embodiment of the present disclosure, the base data includes a base index value of the item, and the base data includes a base index value; determining at least one candidate policy based on the base data and the reference data comprises: and determining at least one candidate strategy according to the attribute information of the item in response to the base index value being lower than the reference index value.

For example, the base index value for an item includes a base exposure amount, a base click amount, and a base conversion rate between the base click amount and the item sales amount for the item. The benchmark index value includes a benchmark exposure, a benchmark click rate, and a benchmark conversion rate for the same type of item within the industry. The attribute information of the item may include graphic description information, price information, etc. of the item.

If the basic exposure of the object is not lower than the reference exposure, but the basic click quantity is lower than the reference click quantity, the image-text description information of the object is possibly not attractive enough, and therefore, a candidate strategy for optimizing the image-text description information of the object can be generated. The candidate strategies can not only contain suggestions for optimizing the image-text information of the article, but also contain concrete keywords, image materials and the like of the suggestions.

If the underlying click rate of the item is not less than the baseline click rate, but the underlying conversion rate is less than the baseline conversion rate, possibly the price of the item is higher, candidate policies for some preferential activities may be generated for the price of the item, which may include specific preferential information, such as giving specific discount information for the item with reference to the price of the peer item, etc.

According to the embodiment, the gap between the average level of the target entity and the belonging industry is determined according to the basic data of the target entity and the basic data of the category of the target entity, so that a target strategy for improving the operation effect of the target entity is generated, and the operation effect of the target entity can be effectively improved.

Fig. 3 is a system architecture diagram of an information presentation method according to one embodiment of the present disclosure.

As shown in fig. 3, the present embodiment includes a database 310, a logic determination module 320, and a question-answer interaction module 330.

The construction of the database 310 includes obtaining basic data of each of a plurality of entities, wherein the entities have category description information; generating category maps of a plurality of entities according to the category description information; and adding the base data and the class map of each of the plurality of entities to a database.

The plurality of entities may be a plurality of electronic stores in an electronic platform. The base data for each entity includes business effect data, business activity data, business status data for that entity, and category description information for the entity. The business effect data may include, among other things, exposure to the item, click rate, click conversion rate, and the like. The business data may include how often the object updates the item, and how often the object requests information in response to the buyer's inquiry for price, delivery date, etc. The business status data may include identity authentication information for the entity, such as whether there is a factory building, whether there is brand authorization, whether it is affiliated with a particular industry zone, and so forth. Each entity has category description information, which may be industry information of the entity, which may be determined based on the item information uploaded by the user, or determined according to industry information filled by the user.

The category similarity among the entities can be calculated according to the category description information of each of the entities in the platform, and the category similarity can represent the similarity of industries of the entities. The greater the class similarity between two entities, the greater the probability that the two entities belong to the same row. Therefore, a plurality of entities can be associated according to the category similarity to obtain a category map (or industry map). For example, at least two entities with category similarity greater than a threshold are associated, resulting in a category map.

Next, the underlying data for each entity in the electronic platform, as well as the category map, may be added to database 310. The basic data and category map of each entity in the database can be updated at intervals of a preset time length.

For example, business effect data may be updated routinely daily, and category maps, business activity data, business status data may be updated routinely weekly.

According to an embodiment of the present disclosure, according to a target problem, acquiring basic data of a target entity and reference data of a category to which the target entity belongs includes: acquiring basic data of a target entity in a plurality of entities according to the target problem; determining basic data of an associated entity associated with the target entity according to the category map; and determining the reference data of the category to which the target entity belongs according to the basic data of the target entity and the basic data of the associated entity.

After extracting the target problem from the input information of the target object, the base data of the target entity and the category map may be obtained from the database 310. From the category map, an entity belonging to the same category as the target entity, i.e., an associated entity associated with the target entity, may be determined. Basic data of the associated entity is obtained, basic data of the target entity and basic data of the associated entity form basic data of a target category, and the target category is the category to which the target entity belongs. Based on the base data of the target class, base data of the target class may be determined. For example, all the basic data belonging to the target class are averaged to obtain the basic data of the target class, and the basic data represent the average level of the basic data of the target class.

The logic judgment module 320 is configured to provide a correct logic judgment based on the obtained basic data and the reference data of the target entity, and output the target policy, so as to support the question-answer interaction module 330 to output correct answer information. The logic determination module 320 includes a logic determination sub-module, an automatic tuning sub-module, and an application pocket bottom sub-module.

The logic judgment submodule is used for triggering logic judgment based on the target problem and outputting a target strategy. Specifically, basic data of the target entity and reference data of a category to which the target entity belongs are acquired, a gap between the target entity and the peer average level is judged based on the basic data and the reference data, and a corresponding target strategy is provided according to the gap. For example, the exposure of the target entity is above the peer average level, but the click rate is below the peer average level, a target policy may be output that suggests to the user to optimize the item master graph or title. For another example, if the exposure and click-through of the target entity are both above the peer average level, but the conversion is below the peer average level, a target policy may be output that suggests optimizing status data (e.g., acquiring corresponding qualification, increasing item update frequency, etc.).

And the automatic tuning sub-module is used for acquiring feedback information of the user and guiding the logic judging sub-module to adjust the target strategy based on the feedback information. For example, for a certain target problem of the user, the logic judging sub-module may determine three candidate policies of policy a, policy B and policy C, and after outputting the policy a as the target policy, obtain feedback information of the user, where the feedback information may represent a positive emotion (such as effective, very effective, etc.) or a negative emotion (such as no effect or no necessity, etc.). When the logic judgment sub-module outputs the target strategy next time aiming at the same or similar problems, the target strategy is adjusted based on the positive emotion/negative emotion fed back by the user last time. For example, if the user feedback is negative, the target policy of the current output is adjusted to be policy B or policy C.

And the application pocket bottom sub-module is used for providing a speaking guide for the user to conduct a correct question when the problem of the user exceeds a preset range (for example, the target problem of the user is irrelevant to the operation condition of the target entity).

The question-answer interaction module 330 may include a generative multi-turn dialog model and a dialog flow interaction sub-module. The generated multi-round dialogue model is used for understanding input information of a user, extracting target questions from the input information, and sending the target questions to the logic judgment module 320, so that the logic judgment module 320 performs logic judgment to obtain a target strategy. After the target strategy is obtained, the generated multi-round dialogue model converts the target strategy into natural language and sends the natural language to the dialogue flow interaction sub-module.

The dialogue flow interaction sub-module provides a dialogue flow interaction window, and displays input information, feedback information and natural language description information of a target strategy of a user in a multi-round dialogue mode.

Fig. 4 is a schematic diagram of a method of generating a dialog flow according to one embodiment of the disclosure.

As shown in fig. 4, the present embodiment includes an interaction layer, a session model, a business logic layer, and a base data layer.

The dialog flow includes input information of the user, such as "i am here for a month, how to feel less colored".

At the interaction layer, input information of a user is received and transmitted to the conversation model. The dialog model may be a generative multi-turn dialog model.

The dialog model receives input information from which a target problem is extracted. For example, the objective problem is "the business effect of the objective entity is desired to be improved". The dialogue model transmits the target problem to the business logic layer, and requests the business logic layer to judge the business logic.

The business logic layer acquires basic data and an industry map from the basic data layer based on the target problem, and carries out business logic judgment based on the basic data and the industry map.

And the basic data layer is used for providing basic data and an industry map and supporting logic judgment of the business logic layer. For example, the basic data of the target entity comprises 5000 target entities for daily exposure, 60 target entities for clicking, 8000 target entities for peer exposure, 45 target entities for clicking, and 85% of response rate of inquiry (peer 65%) ".

The business logic layer judges based on the basic data and the industry map. For example, the business logic layer judges that the exposure rate of the target entity is lower than the level of the same line, the click rate is significantly higher than that of the same line, the business initiative is strong, the target strategy A is output, and the target strategy A is transmitted to the dialogue model.

The dialogue model converts the target strategy a into natural language description information, for example, the natural language description information is "you good", you have already performed good-quality operation in the electronic platform, and have already obtained better effects than most peers, if further promotion is required, promotion according to the strategy a is suggested, and more remarkable effects can be obtained.

The natural language description information output by the dialogue model is used as response information to form a dialogue stream with the input information of the user.

Fig. 5 is a block diagram of an information presentation apparatus according to one embodiment of the present disclosure.

As shown in fig. 5, the information presentation apparatus 500 includes a question determination module 501, a first data acquisition module 502, a response information generation module 503, and a presentation module 504.

The question determination module 501 is configured to determine a target question for a target entity from input information in response to receiving the input information from the target object.

The first data obtaining module 502 is configured to obtain, according to the target problem, base data of the target entity and reference data of a category to which the target entity belongs.

The response information generating module 503 is configured to generate response information of the target problem according to the base data and the reference data.

The display module 504 is configured to display the response information.

The answer information generation module 503 includes a candidate policy determination unit, a target policy determination unit, and an answer information generation unit.

The candidate strategy determining unit is used for determining at least one candidate strategy according to the basic data and the reference data.

The target policy determination unit is configured to determine a target policy from the at least one candidate policy.

The response information generating unit is used for generating natural language description information of the target strategy as response information.

According to an embodiment of the present disclosure, the target entity is associated with at least one item, the base data comprises a base indicator value for the item, and the benchmark data comprises a benchmark indicator value.

The candidate strategy determining unit is used for determining at least one candidate strategy according to the attribute information of the article in response to the basic index value being lower than the reference index value.

The answer information generation module 503 further includes an adjustment unit.

The adjustment unit is used for responding to the feedback information of the target object aiming at the target strategy, and adjusting the weight of the target strategy in at least one candidate strategy according to the feedback information.

The information display device 500 further includes a second data acquisition module, a category map generation module, and a database construction module.

The second data acquisition module is used for acquiring the basic data of each of a plurality of entities, wherein the entities have category description information.

The category map generation module is used for generating category maps of a plurality of entities according to the category description information.

The database construction module is used for adding the basic data and the class patterns of each of the plurality of entities to the database.

The category map generation module includes a similarity determination unit and an association unit.

The similarity determining unit is used for determining the category similarity of the entities according to the category description information.

The association unit is used for associating at least two entities with similarity greater than a threshold value among the plurality of entities to obtain a category map.

The first data acquisition module 502 includes a first basic data acquisition unit, a second basic data acquisition unit, and a reference data acquisition unit.

The first basic data acquisition unit is used for acquiring basic data of a target entity in the plurality of entities according to the target problem.

The second basic data acquisition unit is used for determining basic data of the associated entity associated with the target entity according to the category map.

The reference data acquisition unit is used for determining the reference data of the category to which the target entity belongs according to the basic data of the target entity and the basic data of the associated entity.

The information presentation apparatus 500 also includes a database update module.

The database updating module is used for updating the basic data and the category map of each entity in the database according to the preset time interval.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

Fig. 6 illustrates a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the respective methods and processes described above, such as an information presentation method. For example, in some embodiments, the information presentation method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the information presentation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the information presentation method by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. An information display method, comprising:

in response to receiving input information from a target object, determining a target question for a target entity from the input information;

according to the target problem, basic data of the target entity and reference data of the category to which the target entity belongs are obtained;

generating response information of the target problem according to the basic data and the reference data; and

and displaying the response information.

2. The method of claim 1, wherein the generating response information of the target question from the base data and the reference data comprises:

determining at least one candidate strategy according to the basic data and the reference data;

determining a target policy from the at least one candidate policy; and

And generating natural language description information of the target strategy as the response information.

3. The method of claim 2, wherein the target entity is associated with at least one item, the base data comprises a base indicator value for the item, and the base data comprises a base indicator value; said determining at least one candidate policy from said base data and said reference data comprises:

and determining the at least one candidate strategy according to the attribute information of the article in response to the basic index value being lower than the reference index value.

4. A method according to claim 2 or 3, further comprising:

and in response to receiving feedback information for the target policy from the target object, adjusting the weight of the target policy in the at least one candidate policy according to the feedback information.

5. The method of any one of claims 1 to 4, further comprising:

acquiring basic data of each of a plurality of entities, wherein the entities have category description information;

generating category maps of the entities according to the category description information; and

and adding the basic data of each of the entities and the class patterns to a database.

6. The method of claim 5, wherein the generating a category map for the plurality of entities from the category description information comprises:

determining category similarity among the entities according to the category description information; and

and associating at least two entities with similarity greater than a threshold value among the entities to obtain the category map.

7. The method according to claim 5 or 6, wherein the obtaining, according to the target problem, the base data of the target entity and the base data of the category to which the target entity belongs includes:

acquiring basic data of a target entity in the plurality of entities according to the target problem;

determining basic data of an associated entity associated with the target entity according to the category map; and

and determining the reference data of the category to which the target entity belongs according to the basic data of the target entity and the basic data of the associated entity.

8. The method of any of claims 5 to 7, further comprising:

and updating the basic data of each entity in the database and the category map according to a preset time interval.

9. An information presentation apparatus comprising:

a question determination module for determining a target question for a target entity from input information from a target object in response to receiving the input information;

the first data acquisition module is used for acquiring basic data of the target entity and reference data of a category to which the target entity belongs according to the target problem;

the response information generation module is used for generating response information of the target problem according to the basic data and the reference data; and

and the display module is used for displaying the response information.

10. The apparatus of claim 9, wherein the reply information generation module comprises:

a candidate policy determining unit configured to determine at least one candidate policy according to the base data and the reference data;

a target policy determining unit configured to determine a target policy from the at least one candidate policy; and

and the response information generation unit is used for generating natural language description information of the target strategy as the response information.

11. The apparatus of claim 10, wherein the target entity is associated with at least one item, the base data comprises a base indicator value for the item, and the base data comprises a base indicator value; the candidate strategy determining unit is used for determining the at least one candidate strategy according to the attribute information of the article in response to the basic index value being lower than the reference index value.

12. The apparatus according to claim 10 or 11, wherein the answer information generation module further comprises:

and the adjusting unit is used for responding to the received feedback information of the target object aiming at the target strategy and adjusting the weight of the target strategy in the at least one candidate strategy according to the feedback information.

13. The apparatus of any of claims 9 to 12, further comprising:

the second data acquisition module is used for acquiring the basic data of each of a plurality of entities, wherein the entities have category description information;

the category map generation module is used for generating category maps of the entities according to the category description information; and

and the database construction module is used for adding the basic data of each of the plurality of entities and the category map into a database.

14. The apparatus of claim 13, wherein the category map generation module comprises:

a similarity determining unit, configured to determine a category similarity between the plurality of entities according to the category description information; and

and the association unit is used for associating at least two entities with similarity greater than a threshold value among the plurality of entities to obtain the category map.

15. The apparatus of claim 13 or 14, wherein the first data acquisition module comprises:

a first basic data obtaining unit, configured to obtain basic data of a target entity in the plurality of entities according to the target problem;

the second basic data acquisition unit is used for determining basic data of the associated entity associated with the target entity according to the category map; and

16. The apparatus of any of claims 13 to 15, further comprising:

and the database updating module is used for updating the basic data of each entity in the database and the category map according to a preset time interval.

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.

18. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1 to 8.

19. A computer program product comprising a computer program stored on at least one of a readable storage medium and an electronic device, which, when executed by a processor, implements the method according to any one of claims 1 to 8.