Information query method and device, equipment, medium and program product

Abstract

The invention provides an information query method which can be applied to the technical field of artificial intelligence and the technical field of financial science and technology. The information query method comprises the following steps: receiving user question information sent by a first component; the question information is analyzed, the query intention of the user is determined, and the query intention indicates to obtain multi-dimensional object information of the target object; the query intention is sent to the second component, application interface data sent by the second component are received, the application interface data are determined by the second component based on the query intention, the application interface data comprise respective interface calling addresses of N application systems, and information of at least one dimension of the target object is stored in each application system; and sending the application interface data to the first component, so that the first component executes an application interface calling process based on the interface calling address, and obtains multi-dimensional object information of the target object from the N application systems. The invention further provides an information query device and equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the technical fields of artificial intelligence and fintech, and particularly relates to an information query method, apparatus, device, medium, and program product. Background Art

[0002] In the current customer management system, customer tags are scattered across multiple systems. For example, the information system records basic information, the transaction system retains transaction data, and the customer service system stores service feedback. If a user wants to obtain comprehensive customer information, they have to switch and query repeatedly among these systems. Frequent jumps not only make the operation cumbersome but also consume a large amount of time. This not only reduces work efficiency but also easily misses key information, limiting the accuracy and efficiency of customer recommendations. Summary of the Invention

[0003] In view of the above problems, the present disclosure provides an information query method, apparatus, device, medium, and program product that improve the accuracy and efficiency of customer recommendations.

[0004] According to a first aspect of the present disclosure, there is provided an information query method, including:

[0005] Receiving user question information sent by a first component; parsing the question information to determine the user's query intention, where the query intention indicates obtaining multi-dimensional object information of a target object; sending the query intention to a second component and receiving application interface data sent by the second component, where the application interface data is determined by the second component based on the query intention, and the application interface data includes interface call addresses of N application systems, and at least one dimension of information of the target object is stored in each application system; sending the application interface data to the first component so that the first component executes an application interface call process based on the interface call addresses to obtain multi-dimensional object information of the target object from the N application systems.

[0006] According to an embodiment of the present disclosure, the information query further includes: receiving multi-dimensional object information of the target object and a parsing function matching the multi-dimensional object information sent by a third component; receiving an information query prompt word, where the information query prompt word is related to the multi-dimensional object information of the target object; processing the multi-dimensional object information of the target object using the parsing function and the information query prompt word, and outputting a first information query result related to the information query prompt word.

[0007] According to an embodiment of the present disclosure, determining application interface data based on a query intention includes: obtaining an application interface document, where the application interface document contains M interface call addresses of M application systems, and M is greater than or equal to N; based on the application interface document, determining N interface call addresses of N application systems and request parameters corresponding to the N interface call addresses according to the query intention; generating application interface data according to the interface call addresses and the request parameters.

[0008] According to an embodiment of the present disclosure, the information query further includes: generating a level analysis result of the target object according to the first information query result and the level analysis prompt word, where the level analysis result includes the current level and the next level of the target object; sending the level analysis result to a fourth component so that the fourth component searches for target activity data in the knowledge base, where the target activity data includes activity data that the target object can participate in at the current level and activity data required to reach the next level; processing the target activity data according to the activity analysis prompt word and outputting a second information query result related to the activity analysis prompt word.

[0009] According to an embodiment of the present disclosure, searching for target activity data in the knowledge base includes: vectorizing the level analysis result and retrieving document fragment vectors in the knowledge base that match the conditions of the level analysis result; determining the target activity data according to the document fragment vectors.

[0010] According to an embodiment of the present disclosure, the information query further includes: generating a resource calculation result of the target object according to the first information query result and the resource calculation prompt word, where the resource calculation result includes the monthly average daily resource increase; sending the resource calculation result to a fourth component so that the fourth component searches for target reward data in the knowledge base, where the target reward data includes the amount of resources required for the target object to upgrade from the current level to the next level; processing the target reward data according to the reward analysis prompt word and outputting a third information query result related to the reward analysis prompt word.

[0011] According to an embodiment of the present disclosure, the information query further includes: generating a recommendation strategy for the target object according to any one of the first information query result, the second information query result, or the third information query result in combination with the recommendation strategy prompt word.

[0012] A second aspect of the present disclosure provides an information query device, including: a first receiving module, configured to receive user query information sent by a first component; an analysis module, configured to analyze the query information to determine the user's query intention, where the query intention indicates obtaining multi-dimensional object information of a target object; a first sending module, configured to send the query intention to a second component and receive application interface data sent by the second component, where the application interface data is determined by the second component based on the query intention, and the application interface data includes interface call addresses of N application systems respectively, and at least one dimension of information of the target object is stored in each application system; and a second sending module, configured to send the application interface data to the first component, so that the first component executes an application interface call process based on the interface call address to obtain multi-dimensional object information of the target object from the N application systems.

[0013] A third aspect of the present disclosure provides an electronic device, including: one or more processors; a memory, configured to store one or more computer programs, where the above-mentioned one or more processors execute the above-mentioned one or more computer programs to implement the steps of the above-mentioned method.

[0014] A fourth aspect of the present disclosure further provides a computer-readable storage medium, on which computer programs or instructions are stored, and when the computer programs or instructions are executed by a processor, the steps of the above-mentioned method are implemented.

[0015] A fifth aspect of the present disclosure further provides a computer program product, including computer programs or instructions, and when the computer programs or instructions are executed by a processor, the steps of the above-mentioned method are implemented.

[0016] According to the embodiments of the present disclosure, the large model uses natural language processing capabilities to analyze the user's query intention and improve the accuracy of intention analysis. Collaborate with the second component to determine application interface data related to the query intention. It realizes dynamic matching of different user intentions with corresponding application system interfaces, without the need to manually pre-write a large amount of complex interface adaptation logic, and can quickly adapt to new interfaces, enhancing the flexibility and scalability of the system. The first component executes a call process based on the interface call address provided by the second component and confirmed by the large model, and obtains multi-dimensional object information from N application systems. The interaction between each component and the large model ensures that the data acquisition is comprehensive and orderly, integrates the multi-dimensional object information scattered in different systems, avoids obtaining data from scattered individual systems, and improves the information query efficiency. Each component has a clear division of labor and works in cooperation with the large model to improve the overall performance and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, the above-mentioned content and other objects, features and advantages of the present disclosure will become clearer. In the drawings:

[0018] Figure 1 Schematically shows an application scenario diagram of an information query method, apparatus, device, medium, and program product according to an embodiment of the present disclosure;

[0019] Figure 2 Schematically shows a flowchart of an information query method according to an embodiment of the present disclosure;

[0020] Figure 3 Schematically shows a schematic flowchart of an information query method according to an embodiment of the present disclosure;

[0021] Figure 4 Schematically shows a flowchart of an information query method according to another embodiment of the present disclosure;

[0022] Figure 5 Schematically shows a schematic flowchart of an information query method according to another embodiment of the present disclosure;

[0023] Figure 6 Schematically shows a flowchart of an information query method according to still another embodiment of the present disclosure;

[0024] Figure 7 Schematically shows a schematic flowchart of an information query method according to still another embodiment of the present disclosure;

[0025] Figure 8 Schematically shows a structural block diagram of an information query apparatus according to an embodiment of the present disclosure; and

[0026] Figure 9 Schematically shows a block diagram of an electronic device suitable for implementing the information query method according to an embodiment of the present disclosure. Detailed implementation manners

[0027] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, many specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure. However, it is obvious that one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0028] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0029] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0030] In cases where expressions similar to "at least one of A, B, and C" are used, generally, it should be interpreted according to the meaning commonly understood by those of ordinary skill in the art (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0031] It should be noted that the information query method and device of the present disclosure can be used in the fields of artificial intelligence technology and fintech technology, and can also be used in any field other than the fields of artificial intelligence technology and fintech technology. The present disclosure does not limit the application fields of the information query method and device.

[0032] In the technical solutions of the present disclosure, the user information involved (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties. And the processing of relevant data, such as collection, storage, use, processing, transmission, provision, disclosure, and application, all comply with relevant laws, regulations, and standards, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] In the scenario of making automated decisions using personal information, the methods, devices, and systems provided by the embodiments of the present disclosure all provide corresponding operation entrances for users to choose to agree or refuse the results of automated decisions; if the user chooses to refuse, the expert decision-making process will be entered. The expression "automated decision" herein refers to the activity of automatically analyzing and evaluating an individual's behavior habits, interests, or economic, health, credit status, etc. through a computer program and making a decision. The expression "expert decision" herein refers to the activity of making a decision by a person who specializes in a certain field, has specialized experience, knowledge, and skills, and has reached a certain professional level.

[0034] Embodiments of the present disclosure provide an information query method, including: receiving user query information sent by a first component; parsing the query information to determine the user's query intention, where the query intention indicates obtaining multi-dimensional object information of a target object; sending the query intention to a second component and receiving application interface data sent by the second component, where the application interface data is determined by the second component based on the query intention, and the application interface data includes interface call addresses of N application systems respectively, and at least one dimension of information of the target object is stored in each application system; sending the application interface data to the first component, so that the first component executes an application interface call process based on the interface call addresses and obtains multi-dimensional object information of the target object from the N application systems.

[0035] Figure 1 FIG. schematically shows an application scenario diagram of the information query method according to an embodiment of the present disclosure.

[0036] As Figure 1 shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0037] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0038] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0039] The server 105 may be a server providing various services, such as a background management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (only for example). The background management server may analyze and process data such as received user requests, and feedback the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0040] It should be noted that the information query method provided by the embodiments of the present disclosure can generally be executed by the server 105. Correspondingly, the information query device provided by the embodiments of the present disclosure can generally be set in the server 105. The information query method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Correspondingly, the information query device provided by the embodiments of the present disclosure can also be set in a server or a server cluster different from the server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105.

[0041] It should be understood that Figure 1 the numbers of the terminal devices, networks, and servers in

[0042] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers. Figure 1 Based on the Figures 2 to 7 scenario described below, the information query method of the disclosed embodiments will be described in detail through

[0043] Figure 2 FIG. schematically shows a flowchart of the information query method according to the embodiments of the present disclosure.

[0044] As Figure 2 shown, the information query of this embodiment includes operations S210 to S240, which are executed by the large model.

[0045] In operation S210, user question information sent by the first component is received.

[0046] According to the embodiments of the present disclosure, the first component is used to receive user question information and can preliminarily collect, organize, or analyze the user question information. The user can be a staff member with the permission to operate the system. The user interacts with the large model by asking questions and can directly obtain information about the target object corresponding to the question through natural language. The user's question can be directed to any customer. The user can query the required information by asking questions.

[0047] For example, in the e-commerce field, various information such as the sales volume, sales amount, inventory turnover rate, and favorable comment rate of various products is queried through user questions. In the field of workplace recruitment, information such as the education background, major, work experience, skill certificates, expected salary, and expected work location of job seekers is queried. In the tourism field, information such as the historical travel destinations of tourists, travel methods (independent travel or group tour), consumption amount, stay time, and evaluations of scenic spots and hotels is queried. In the education field, information such as the course learning progress of students, completion of homework, examination results, and the degree of mastery of each knowledge point is queried.

[0048] In operation S220, the question information is parsed to determine the user's query intention, where the query intention indicates obtaining multi-dimensional object information of the target object.

[0049] According to an embodiment of the present disclosure, after receiving the question information sent by the first component, the large model performs semantic understanding and intention recognition on the question information to obtain the query intention. The target object is used to represent the relevant customer in the question information. The multi-dimensional object information is used to represent the relevant dimensional information of the relevant customer in the question information. For example, the six dimensions of the historical travel destinations of tourists, travel methods (independent travel or group tour), consumption amount, stay time, and evaluations of scenic spots and hotels in the above example.

[0050] In operation S230, the query intention is sent to the second component, and the application interface data sent by the second component is received, where the application interface data is determined by the second component based on the query intention, and the application interface data includes the interface call addresses of N application systems respectively, and at least one dimension of information of the target object is stored in each application system.

[0051] According to an embodiment of the present disclosure, the large model sends the recognized query intention to the second component. After receiving the query intention, the second component determines which application systems to obtain data from according to its own logic and configuration. These application systems store information of different dimensions of the target object. For example, in the financial field, there may be a system storing customer basic information and another recording customer consumption behavior data. After the second component determines the required application systems, it sorts out the interface call addresses of these application systems respectively, and these addresses form the application interface data. The first component can subsequently use these addresses to obtain information of different dimensions of the target object from each application system to meet the query intention. For example, through these interface call addresses, multi-dimensional information such as the age, region, and past participation in activities of customers is obtained from different systems to complete the construction of the customer portrait.

[0052] In operation S240, the application interface data is sent to the first component so that the first component executes the application interface call process based on the interface call addresses to obtain the multi-dimensional object information of the target object from the N application systems.

[0053] According to an embodiment of the present disclosure, after obtaining application interface data containing the interface call addresses of N application systems, these data will be sent to the first component. The first component starts the application interface call process based on the interface call address, and establishes contact with the N application systems in turn. By interacting with the N application systems, the first component can obtain specific dimensional information related to the target object from each application system. Since each application system stores information about at least one dimension of the target object, when the first component successfully calls the interfaces of all relevant application systems, it can integrate and obtain the multi-dimensional object information of the target object.

[0054] According to the embodiments of the present disclosure, the big model uses natural language processing capabilities to parse user query intent and improve the accuracy of intent parsing. Collaborate with the second component to determine the application interface data related to the query intent. Dynamic matching of different user intents and corresponding application system interfaces is achieved, without the need to manually pre-write a large amount of complex interface adaptation logic, and new interfaces can be quickly adapted to enhance system flexibility and scalability. The first component executes the call process based on the interface call address confirmed by the big model provided by the second component, and obtains multi-dimensional object information from N application systems. The interaction between each component and the big model ensures that data acquisition is comprehensive and orderly, integrates multi-dimensional object information scattered in different systems, avoids obtaining data from scattered systems, and improves information query efficiency. Each component has a clear division of labor and works in collaboration with the big model to improve the overall performance and stability of the system.

[0055] Figure 3 The flowchart of the information query method according to the embodiment of the present disclosure is schematically shown.

[0056] like Figure 3 As shown, the information query method of the embodiment of the present disclosure also includes steps 11 to 13.

[0057] Step 11: Receive the multi-dimensional object information of the target object sent by the third component, and the parsing function matching the multi-dimensional object information.

[0058] According to the embodiments of the present disclosure, Figure 3 As shown, after obtaining the multi-dimensional object information of the target object according to the above method, the first component initiates a parsing request to the third component to request the third component to obtain a parsing function matching the multi-dimensional object information. At the same time, the multi-dimensional object information of the target object is sent.

[0059] According to an embodiment of the present disclosure, a parsing function is a program code segment for processing and interpreting the above-mentioned multi-dimensional object information. Each parsing function is matched with specific multi-dimensional object information, and its purpose is to further process and transform the obtained multi-dimensional object information to meet the processing requirements of the large model. For example, for the customer's consumption behavior information, there may be a parsing function for calculating the customer's consumption activity score; for the customer's interest preference information, there may be another parsing function to convert it into a more understandable and analyzable label form. By receiving these parsing functions, the receiver can use them to accurately analyze and process the corresponding multi-dimensional object information, providing valuable data for subsequent decision-making, display, or other business operations. And, perform format conversion, for example, convert it into the json format.

[0060] Step 12: Receive an information query prompt, where the information query prompt is related to the multi-dimensional object information of the target object.

[0061] According to an embodiment of the present disclosure, the information query prompt can be directly received by the large model, or the information query prompt can be sent to the first component first, and the first component integrates the information query prompt and the multi-dimensional object information and sends them to the large model together. The information query prompt is an instruction issued by the user or other system modules, used to guide the large model to perform semantic understanding and query result output. Among them, the above-mentioned information related to the customer is obtained under the authorization and consent of the target object and stored in the database.

[0062] Step 13: Use the parsing function and the information query prompt to process the multi-dimensional object information of the target object, and output a first information query result related to the information query prompt.

[0063] According to an embodiment of the present disclosure, use the parsing function to process the multi-dimensional object information, convert it into a data format convenient for the large model to process, so that the large model can more efficiently understand and analyze this information. And, after completing the data format conversion, use the information query prompt to process the multi-dimensional object information of the target object that has been processed into a suitable format. To further screen, analyze, etc. the data adapted to the large model according to the specific query requirements included in the prompt, so as to obtain a first information query result that meets the specific query requirements.

[0064] According to an embodiment of the present disclosure, determining application interface data based on the query intention includes steps 21 to 23.

[0065] Step 21: Obtain an application interface document, where the application interface document contains M interface call addresses of M application systems, and M is greater than or equal to N.

[0066] Step 22: Based on the application interface document, determine the N interface call addresses of N application systems and the request parameters corresponding to the N interface call addresses according to the query intent.

[0067] According to an embodiment of the present disclosure, from the M application system interface addresses included in the application interface document according to the received query intent, select the N interface call addresses of the N application systems actually required for this query. And, for the determined N interface call addresses, determine the corresponding request parameters respectively. Different interfaces may require different parameters to accurately obtain the required data. For example, a certain customer information query interface may require the customer ID as a request parameter, then clarify these parameter values according to the query intent to ensure that the interface can be correctly called to obtain accurate data.

[0068] Step 23: Generate application interface data according to the interface call address and the request parameters.

[0069] According to an embodiment of the present disclosure, the second component integrates the determined interface call address and the corresponding request parameters to generate application interface data.

[0070] Figure 4 Schematically shows a flowchart of an information query method according to another embodiment of the present disclosure. Figure 5 Schematically shows a schematic flowchart of an information query method according to another embodiment of the present disclosure. The following combines Figure 4 and Figure 5 for a detailed description.

[0071] As Figure 4 shown, after performing the above operations S210 to S240, the information query method further includes operations S410 to S430.

[0072] In operation S410, generate a level analysis result of the target object according to the first information query result and the level analysis prompt word, where the level analysis result includes the current level and the next level of the target object.

[0073] According to an embodiment of the present disclosure, the level analysis prompt word is a preset instruction for guiding the level analysis process. For example, in customer level division, the level analysis prompt word may be "extract the required storage amount today to reach the next reward level, the current reward points, and the reward points information for the next reward level in the first information query result", which clarifies the dimensions and rules for analysis. Using the first information query result as the data source, process according to the rules specified by the level analysis prompt word.

[0074] According to an embodiment of the present disclosure, the above content is summarized to finally generate a level analysis result, which includes the current level and the next level of the target object. Among them, the current level reflects the current level where the target object is located, and the next level is based on the current data and promotion conditions, and calculates the minimum requirements that the target object needs to meet to be promoted to the next level. For example, according to the level analysis prompt words and the first information query result (the customer's current stored amount is 17W, the current level is four-star, and the integral is 5000 points, and the stored amount required for the next level of five-star is 20W and the bonus integral is 10000 points), the amount of money that customer A needs to store today to reach the next reward level (3W), the current reward integral (5000 points), and the integral information obtained at the next reward level (10000 points) are obtained.

[0075] In operation S420, the level analysis result is sent to the fourth component so that the fourth component searches for target activity data from the knowledge base, where the target activity data includes the activity data that can be participated in by the target object at the current level and the activity data for meeting the standards at the next level.

[0076] According to an embodiment of the present disclosure, the level analysis result is sent to the fourth component so that the fourth component searches for target activity data from the knowledge base by calling other components. The other component can be the fifth component, which is used to obtain the target activity data from the knowledge base and send it to the sixth component. The other component also includes the sixth component, which is used to interact with the large model, send the target activity data to the large model, and receive the activity analysis result returned by the large model. Among them, the sixth component can also receive the activity analysis prompt words and send them to the large model.

[0077] According to an embodiment of the present disclosure, the large model sends the generated level analysis result of the target object (including the current level and the next level) to the fourth component. This level analysis result is a summary of the level where the target object is located and the promotion direction, and it provides key information for the subsequent operations of the fourth component. After receiving the level analysis result, the fourth component searches for target activity data from the knowledge base based on it.

[0078] According to an embodiment of the present disclosure, a large amount of information related to various activities is stored in the knowledge base. The fourth component filters out specific activity data according to the current level and the next level of the target object. Among them, the "activity data that can be participated in at the current level" refers to the activity information that the target object can participate in based on the existing level status, such as the following activity name, time, location, etc.; the "activity data for meeting the standards at the next level" refers to the activity-related information that the target object needs to participate in to reach the next level, such as completing specific tasks, consuming a certain amount of money, etc.

[0079] According to an embodiment of the present disclosure, searching for target activity data from the knowledge base includes steps 31 to 32.

[0080] Step 31: Vectorize the level analysis result and retrieve the document fragment vectors in the knowledge base that match the conditions of the level analysis result.

[0081] Step 32: Determine the target activity data according to the document fragment vectors.

[0082] According to an embodiment of the present disclosure, relevant document paragraphs are recalled respectively using keyword retrieval and vector retrieval according to the level analysis result; the retrieved document paragraphs are de-duplicated and then merged according to the policy set by the parameters; a full-scale retrieval of the existing activities in the knowledge base is performed, and the activities that match the current level and the next level are used as the best benefit activities that the target object can participate in at the current level and the next-stage compliance benefit activities. Among them, the next-stage compliance benefit activity means that after the target object participates in this activity, it can be upgraded to the next level.

[0083] According to an embodiment of the present disclosure, determining the target activity data according to the document fragment vectors realizes the function of accurately extracting the required information from the knowledge base. Since the retrieved document fragment vectors already match the conditions of the level analysis result, based on these vectors, the corresponding activity data can be directly located, such as the specific activity name, rules, participation conditions, etc. This ensures that the obtained target activity data is highly relevant to the level status of the target object and meets the business requirements for personalized activity recommendation or analysis. This way of determining the target activity data based on vector matching makes it highly adaptable when facing the update and expansion of the knowledge base. As long as the newly added activity data is reasonably vectorized during entry, the relevant information can be found through the same vector matching mechanism without large-scale modification of the retrieval and data determination logic, improving the scalability and flexibility of the system.

[0084] In operation S430, the target activity data is processed according to the activity analysis prompt words, and a second information query result related to the activity analysis prompt words is output.

[0085] According to an embodiment of the present disclosure, after the target activity data is obtained, the fourth component processes these data according to the "activity analysis prompt words". The activity analysis prompt words clarify the analysis direction and requirements for the target activity data. For example, the prompt words may be "summarize the activity platforms, activity themes, activity levels, activity objects, activity contents, activity times, and precautions of the activities that the target object can participate in". The fourth component will perform operations such as screening and filtering on the target activity data according to this requirement. After the above processing, the fourth component outputs a "second information query result related to the activity analysis prompt words". This result is obtained by processing the target activity data according to the requirements of the activity analysis prompt words and can meet specific business needs, such as providing activity recommendations that meet the target object's level and specific conditions.

[0086] Figure 6 Schematically shows a flowchart of an information query method according to another embodiment of the present disclosure. Figure 7 Schematically shows a schematic diagram of the process of an information query method according to another embodiment of the present disclosure. The following will be described in detail in conjunction with Figure 6 and Figure 7 for a detailed description.

[0087] As Figure 6 shown, after performing the above operations S210 to S240, the information query method further includes operations S610 to S630.

[0088] In operation S610, according to the first information query result and the resource calculation prompt word, generate the resource calculation result of the target object, where the resource calculation result includes the monthly average daily resource increase amount.

[0089] According to an embodiment of the present disclosure, the monthly average daily resource increase amount is a key indicator for judging the resource growth situation of the target object. It is calculated based on the monthly average daily assets of this month and the monthly average daily assets of last month. Among them, the first information query result includes information such as the monthly average daily assets of this month and the monthly average daily assets of last month of the target object. The large model calculates the monthly average daily resource increase amount of the target customer based on the monthly average daily assets of this month and the monthly average daily assets of last month of the target object. The monthly average daily resource increase amount is equal to the monthly average daily assets of this month minus the monthly average daily assets of last month.

[0090] According to an embodiment of the present disclosure, query the lowest amount of the next level corresponding to the reward level of the monthly average daily asset increase value. For example, the basic information of customer A has been obtained, including the current monthly average daily storage amount of 80W. By querying the knowledge base, it is found that the next level corresponding to the five-star level, the six-star level, requires a storage amount of 100W to 600W. Therefore, the large model calculates that the customer needs to store at least 20W at this time.

[0091] According to an embodiment of the present disclosure, based on the standard statement and the monthly average daily resource increase amount, use the second component to professionalize the user's question information. For example, the input monthly average daily resource increase amount is 20W, and the standard statement is: XX is the monthly average daily resource increase amount, and I need to query the reward conditions related to the monthly average daily resource increase amount of 20W. The large model processes it and outputs the result.

[0092] In operation S620, send the resource calculation result to the fourth component so that the fourth component searches for the target reward data in the knowledge base, where the target reward data includes the amount of resources required for the target object to upgrade from the current level to the next level.

[0093] According to an embodiment of the present disclosure, the resource calculation result is sent to a fourth component, so that the fourth component searches for target reward data from a knowledge base by invoking other components. The other component may be a seventh component, which summarizes the monthly average daily resource increment and the reward points corresponding to the monthly average daily resource increment and sends them to a third component, and then the third component sends them to a large model. Among them, an eighth component queries the level according to the prompt word for querying the monthly average daily resource increment; a ninth component queries the reward points corresponding to the level according to the prompt word for querying the reward points corresponding to the monthly average daily resource increment. The seventh component summarizes them to obtain the target reward data and sends it to the large model.

[0094] In operation S630, the target reward data is processed according to the reward analysis prompt word, and a third information query result related to the reward analysis prompt word is output.

[0095] According to an embodiment of the present disclosure, after the fourth component obtains the target reward data, it processes these data according to the reward analysis prompt word. The reward analysis prompt word indicates the analysis method and output requirements for the target reward data. If the reward conditions corresponding to the monthly average daily resource increase can be queried in the knowledge database, the prompt word may be: Sort out the reward conditions corresponding to the monthly average daily asset increase according to [target reward data] and output. If the reward conditions corresponding to the monthly average daily resource increase cannot be queried in the knowledge database, the prompt word may be: The relevant information found in the knowledge base in the above [target reward data] can only be answered in combination with the above information. If the above content is empty or no relevant content is found therein, then reply "No relevant content found", and you cannot play on your own based on your own knowledge.

[0096] According to an embodiment of the present disclosure, the reward analysis prompt word may also be:

[0097] If the highest reward level has been reached, output "The highest reward level has been reached".

[0098] If the points available for the current level do not exist, then it is 0.

[0099] Only the points available for the current level, the points available for the next level, and the minimum amount required for the next level need to be output. Other data does not need to be calculated, and no extra content needs to be output.

[0100] According to an embodiment of the present disclosure, the third information query result is, for example: The customer number is 2000XXXXX16056, the difference between the average daily assets this month and last month is 10W, currently meets the third-level reward level, the points available for the current level: 5000 points, the points available for the next level 10000 points, and the amount that needs to be stored today to reach the next reward level: 5W.

[0101] According to an embodiment of the present disclosure, the third information query result is determined based on a specific resource increase amount or integral increase amount, and can provide targeted information support for related services. For example, it helps staff understand the characteristics of the resource upgrade needs of different target objects, so as to recommend more reasonable recommendation strategies for different target objects.

[0102] According to an embodiment of the present disclosure, the information query method further includes step 41.

[0103] In step 41, based on any one of the first information query result, the second information query result, or the third information query result, combined with the recommendation strategy prompt words, a recommendation strategy for the target object is generated.

[0104] According to an embodiment of the present disclosure, the recommendation strategy prompt words are preset to guide the generation direction of the recommendation strategy. For example, "Based on the income level, consumption habits, financial management preferences, and recent behaviors of the target object, recommend suitable financial products and services for the customer; and generate the recommendation words for this financial product or service."

[0105] According to an embodiment of the present disclosure, the recommendation strategy prompt words are input into the second component, and through the collaborative action of the second component and the large model, a recommendation strategy or recommendation words suitable for the target object are generated. The recommendation words can be, for example: "Dear customer (target object), XX institution is carrying out a resource upgrade and integral feedback activity. Your assets in our institution have reached the standard, and you can currently obtain XXX points. If you increase XXX resource amount in our bank and keep it until the end of the period, you can obtain an additional XXX points. The points can be exchanged for deductions, phone bills, etc. Registration method: Log in to the mobile APP to learn more details. We sincerely invite your participation."

[0106] According to an embodiment of the present disclosure, based on the first information query result, that is, based on the portrait of the target object, combined with the recommendation strategy prompt words, a recommendation strategy for the target object is generated. Since the first information query result is the recommendation words generated based on the portrait of the target object, the classification of the recommendation words is less, and it shows a more general expression of the words.

[0107] According to an embodiment of the present disclosure, based on the second information query result, that is, based on the portrait of the target object, combined with the recommendation strategy prompt words, a recommendation strategy for the target object is generated. Since the second information query result is the recommendation words generated based on the target object level, the recommendation words are to encourage the target object to participate in the activity to obtain rewards or upgrades.

[0108] According to an embodiment of the present disclosure, the recommendation strategy is centered around activities. The recommendation strategy can be to push notifications for offline new product experience activities and provide an exclusive priority registration channel for the activities to attract participation. For customers who need to upgrade their levels, emphasize the attractiveness of the next-level attainment activities, such as informing that a limited gift can be obtained after completing the activity of signing in continuously for 30 days to motivate customers to participate.

[0109] According to an embodiment of the present disclosure, based on the third information query result, that is, based on the portrait of the target object and in combination with the recommendation strategy prompt words, a recommendation strategy for the target object is generated. Since the third information query result is a recommended speech generated based on the resource increase amount of the target object, the recommended speech is to motivate the target object to obtain rewards or upgrades by increasing the resource amount.

[0110] According to an embodiment of the present disclosure, by generating recommendation strategies based on different information query results, the diverse needs of users are met. Based on the first information query result, recommended speech is generated according to the general portrait, which can provide basic and widely applicable recommendations for users, covering the common needs of most users; based on the second information query result, recommended speech is generated around the level to motivate users to participate in activities to obtain rewards or upgrades, which is very attractive to users with the need to improve their levels; based on the third information query result, recommended speech is generated according to the resource increase amount to encourage users to increase resources to obtain rewards, providing precise guidance for users who focus on resource accumulation and comprehensively improving users' satisfaction with the recommended content.

[0111] According to an embodiment of the present disclosure, through the collaboration between the large model and each component, recommendation strategies and recommended speech can be automatically generated according to specific rules and different information query results without manual analysis and formulation of recommended content one by one. Thus, manual intervention is reduced, operation efficiency is improved, and labor costs are reduced. At the same time, precise recommendation improves the recommendation hit rate, reduces ineffective recommendations, and lowers marketing costs. For recommended speech in different situations, it stimulates user participation. Informing users that they can obtain rewards or upgrades by participating in activities, as well as obtaining rewards by increasing resources, encourages users to actively participate in platform activities, improves the activity and retention rate of users on the platform, forms a positive interaction between users and the platform, and enhances user stickiness.

[0112] Based on the above information query method, the present disclosure also provides an information query device. The following will be combined with Figure 8 to describe this device in detail.

[0113] Figure 8 The structural block diagram of the information query device according to an embodiment of the present disclosure is schematically shown.

[0114] As Figure 8As shown in the figure, the information query device 800 of this embodiment includes a first receiving module 810, a parsing module 820, a first sending module 830, and a second sending module 840.

[0115] The first receiving module 810 is configured to receive the user's question information sent by the first component. In one embodiment, the first receiving module 810 can be used to perform the operation S210 described above, which will not be elaborated here.

[0116] The parsing module 820 is configured to parse the question information to determine the user's query intent, where the query intent indicates obtaining multi-dimensional object information of the target object. In one embodiment, the parsing module 820 can be used to perform the operation S220 described above, which will not be elaborated here.

[0117] The first sending module 830 is configured to send the query intent to the second component and receive the application interface data sent by the second component, where the application interface data is determined by the second component based on the query intent, and the application interface data includes the interface call addresses of N application systems, and at least one dimension of information of the target object is stored in each application system. In one embodiment, the first sending module 830 can be used to perform the operation S230 described above, which will not be elaborated here.

[0118] The second sending module 840 is configured to send the application interface data to the first component, so that the first component executes the application interface call process based on the interface call address and obtains the multi-dimensional object information of the target object from the N application systems. In one embodiment, the second sending module 840 can be used to perform the operation S840 described above, which will not be elaborated here.

[0119] According to the embodiments of the present disclosure, the large model uses the parsing module to process natural language to parse the user's query intent, improving the accuracy of intent parsing. The first sending module cooperates with the second component to determine the application interface data related to the query intent. It realizes dynamic matching of different user intents with corresponding application system interfaces, without the need to manually pre-write a large number of complex interface adaptation logics, and can quickly adapt to new interfaces, enhancing the flexibility and scalability of the system. Through the cooperation of the second sending module and the first component, according to the interface call address provided by the second component and confirmed by the large model, the call process is executed to obtain multi-dimensional object information from the N application systems. The interaction between each component and the large model ensures that the data acquisition is comprehensive and orderly, integrating the multi-dimensional object information scattered in different systems, avoiding obtaining data from scattered individual systems, and improving the information query efficiency. Each component has a clear division of labor and works in cooperation with the large model, improving the overall performance and stability of the system.

[0120] According to the embodiments of the present disclosure, the information query device further includes a second receiving module, a third receiving module, and a first processing module.

[0121] A second receiving module, configured to receive multi-dimensional object information of a target object sent by a third component, as well as a parsing function matching the multi-dimensional object information.

[0122] A third receiving module, configured to receive an information query prompt word, where the information query prompt word is related to the multi-dimensional object information of the target object; a first processing module, configured to process the multi-dimensional object information of the target object by using the parsing function and the information query prompt word, and output a first information query result related to the information query prompt word.

[0123] According to an embodiment of the present disclosure, determining application interface data based on a query intention includes: an obtaining module, a first determining module, and a first generating module.

[0124] The obtaining module is configured to obtain an application interface document, where the application interface document includes M interface call addresses of M application systems, and M is greater than or equal to N.

[0125] The first determining module is configured to determine N interface call addresses of N application systems and request parameters corresponding to the N interface call addresses based on the application interface document according to the query intention.

[0126] The first generating module is configured to generate application interface data according to the interface call addresses and the request parameters.

[0127] According to an embodiment of the present disclosure, the information query device further includes: a second generating module, a third sending module, and a second processing module.

[0128] The second generating module is configured to generate a level analysis result of the target object according to the first information query result and a level analysis prompt word, where the level analysis result includes the current level and the next level of the target object.

[0129] The third sending module is configured to send the level analysis result to a fourth component, so that the fourth component searches for target activity data in a knowledge base, where the target activity data includes activity data that can be participated in at the current level of the target object and activity data for reaching the standard at the next level.

[0130] The second processing module is configured to process the target activity data according to an activity analysis prompt word, and output a second information query result related to the activity analysis prompt word.

[0131] According to an embodiment of the present disclosure, searching for target activity data in a knowledge base includes: a vectorizing module and a second determining module.

[0132] The vectorizing module is configured to vectorize the level analysis result and retrieve document fragment vectors in the knowledge base that match the conditions of the level analysis result.

[0133] A second determination module, configured to determine target activity data according to the document fragment vector.

[0134] According to an embodiment of the present disclosure, the information query device further includes: a third generation module, a fourth sending module, and a third processing module.

[0135] The third generation module is configured to generate a resource calculation result of the target object according to the first information query result and the resource calculation prompt word, where the resource calculation result includes the monthly average daily resource increase.

[0136] The fourth sending module is configured to send the resource calculation result to the fourth component, so that the fourth component searches for target reward data from the knowledge base, where the target reward data includes the amount of resources required for the target object to upgrade from the current level to the next level; the third processing module is configured to process the target reward data according to the reward analysis prompt word and output a third information query result related to the reward analysis prompt word.

[0137] According to an embodiment of the present disclosure, the information query device further includes: a fourth generation module.

[0138] The fourth generation module is configured to generate a recommendation strategy for the target object according to any one of the first information query result, the second information query result, or the third information query result, in combination with the recommendation strategy prompt word.

[0139] According to an embodiment of the present disclosure, any multiple of the first receiving module 810, the parsing module 820, the first sending module 830, and the second sending module 840 may be combined and implemented in one module, or any one of them may be split into multiple modules. Or, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first receiving module 810, the parsing module 820, the first sending module 830, and the second sending module 840 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or may be implemented by any other reasonable way of integrating or packaging circuits, etc., in hardware or firmware, or implemented in any one of the three implementation ways of software, hardware, and firmware, or in any appropriate combination of them. Or, at least one of the first receiving module 810, the parsing module 820, the first sending module 830, and the second sending module 840 may be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding functions may be executed.

[0140] Figure 9A block diagram of an electronic device suitable for implementing an information query method according to an embodiment of the present disclosure is schematically shown.

[0141] As Figure 9 shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage section 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include on-board memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0142] In the RAM 903, various programs and data required for the operation of the electronic device 900 are stored. The processor 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. The processor 901 executes various operations of the method flow according to an embodiment of the present disclosure by executing the programs in the ROM 902 and / or the RAM 903. It should be noted that the programs may also be stored in one or more memories other than the ROM 902 and the RAM 903. The processor 901 may also execute various operations of the method flow according to an embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0143] According to an embodiment of the present disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, and the input / output (I / O) interface 905 is also connected to the bus 904. The electronic device 900 may further include one or more of the following components connected to the input / output (I / O) interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed so that a computer program read from it can be installed into the storage section 908 as needed.

[0144] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the one or more programs are executed, the methods according to the embodiments of the present disclosure are implemented.

[0145] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the above-described ROM 902 and / or RAM 903 and / or one or more memories other than ROM 902 and RAM 903.

[0146] Embodiments of the present disclosure further include a computer program product, which includes a computer program, and the computer program includes program code for executing the method shown in the flowchart. When the computer program product runs in a computer system, the program code is used to cause the computer system to implement the information query method provided by the embodiments of the present disclosure.

[0147] When the computer program is executed by the processor 901, the above functions defined in the system / apparatus of the embodiments of the present disclosure are executed. According to an embodiment of the present disclosure, the above-described systems, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0148] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and be downloaded and installed through the communication part 909, and / or be installed from the removable medium 911. The program code included in the computer program may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0149] In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, the above-mentioned functions defined in the system of the embodiments of the present disclosure are performed. According to the embodiments of the present disclosure, the above-described systems, devices, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0150] According to the embodiments of the present disclosure, the program code for executing the computer program provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, such as Java, C++, python, the "C" language, or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, by connecting through the Internet using an Internet service provider).

[0151] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0152] Those skilled in the art can understand that the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0153] The embodiments of the present disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments have been described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. An information query method, characterized in that: The method comprises: Receiving user question information sent by the first component; Parsing the question information to determine the user's query intention, wherein the query intention indicates obtaining multi-dimensional object information of a target object; Sending the query intent to the second component, and receiving application interface data sent by the second component, wherein the application interface data is determined by the second component based on the query intent, and the application interface data includes interface call addresses of N application systems, each of which stores information of at least one dimension of the target object; The application interface data is sent to the first component, so that the first component executes an application interface calling process based on the interface calling address, and obtains multi-dimensional object information of the target object from the N application systems.

2. The method according to claim 1, characterized in that The method further comprises: Receiving multi-dimensional object information of the target object sent by a third component, and a parsing function matching the multi-dimensional object information; receiving an information query prompt word, wherein the information query prompt word is related to the multi-dimensional object information of the target object; The multi-dimensional object information of the target object is processed using the analytical function and the information query prompt word, and a first information query result related to the information query prompt word is output.

3. The method according to claim 1, characterized in that Determining the application interface data based on the query intent includes: Obtaining an application interface document, wherein the application interface document includes M interface call addresses of M application systems, where M is greater than or equal to N; Based on the application interface document, determine N interface call addresses of the N application systems and request parameters corresponding to the N interface call addresses according to the query intent; The application interface data is generated according to the interface call address and the request parameters.

4. The method according to claim 2, characterized in that: The method further comprises: Generating a level analysis result of the target object according to the first information query result and the level analysis prompt word, wherein the level analysis result includes a current level and a next level of the target object; Sending the level analysis result to a fourth component so that the fourth component searches for target activity data from a knowledge base, wherein the target activity data includes activity data that the target object can participate in at the current level and activity data that meets the requirements for the next level; The target activity data is processed according to the activity analysis prompt word, and a second information query result related to the activity analysis prompt word is output.

5. The method according to claim 4, characterized in that Search for target activity data from the knowledge base, including: Vectorizing the hierarchical analysis result, and retrieving document fragment vectors matching the hierarchical analysis result condition in the knowledge base; The target activity data is determined according to the document fragment vector.

6. The method according to claim 2, characterized in that The method further comprises: Generate a resource calculation result of the target object according to the first information query result and the resource calculation prompt word, wherein the resource calculation result includes a monthly average daily resource increase; Sending the resource calculation result to a fourth component so that the fourth component searches for target reward data from the knowledge base, wherein the target reward data includes the amount of resources required for the target object to upgrade from a current level to a next level; The target reward data is processed according to the reward analysis prompt word, and a third information query result related to the reward analysis prompt word is output.

7. The method according to any one of claims 2, 4 or 6, characterized in that: The method further comprises: A recommendation strategy for a target object is generated according to any one of the first information query result, the second information query result or the third information query result in combination with a recommendation strategy prompt word.

8. An information query device, characterized in that: The device comprises: A first receiving module, used to receive user question information sent by the first component; A parsing module, used to parse the question information and determine the query intention of the user, wherein the query intention indicates obtaining multi-dimensional object information of a target object; a first sending module, configured to send the query intent to the second component, and receive application interface data sent by the second component, wherein the application interface data is determined by the second component based on the query intent, and the application interface data includes interface call addresses of N application systems, each of which stores information of at least one dimension of the target object; and The second sending module is used to send the application interface data to the first component, so that the first component executes the application interface calling process based on the interface calling address and obtains the multi-dimensional object information of the target object from the N application systems.

9. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images