An information acquisition method, apparatus, device, and storage medium

Abstract

This disclosure provides an information collection method, apparatus, device, and storage medium, relating to the field of artificial intelligence, and particularly to the field of AI applications. The specific implementation scheme is as follows: receiving a user's request for an information collection task; determining a pre-configured step tree for the information collection task, the step tree including multiple collection nodes, each collection node associated with a collection question in the information collection task; determining an initial collection node, and iteratively executing the collection process starting from the initial collection node until a preset termination condition is met; each iteration includes: generating and returning a corresponding collection question to the user based on the current collection node; obtaining the user's answer to the collection question; and determining the next collection node based on the answer information, the type of the current collection node, and preset node jump rules. This method can significantly improve the efficiency and accuracy of information collection.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to AI application technology, specifically to an information acquisition method, device, equipment, and storage medium. Background Technology

[0002] In the field of artificial intelligence, intelligent dialogue systems, personalized recommendation engines, and various consulting agents (such as intelligent customer service, educational consultants, and health assistants) have been widely applied. These agents typically require multiple rounds of interaction with users to collect necessary contextual information in order to provide accurate services or decisions. Currently, common techniques for achieving this information collection largely rely on pre-programmed linear dialogue scripts or simple rule branches. Summary of the Invention

[0003] This disclosure provides an information acquisition method, apparatus, device, and storage medium.

[0004] According to one aspect of this disclosure, an information collection method is provided, comprising: Receive user requests for information collection tasks; A step tree pre-configured for the information collection task is determined, the step tree including multiple collection nodes, each collection node being associated with a collection question in the information collection task; Determine the initial acquisition node, and starting from the initial acquisition node, execute the acquisition process iteratively until a preset termination condition is met; each iteration includes: Based on the current data collection node, generate and return the corresponding data collection question to the user; Obtain the user's answer information to the collected questions; Based on the response information, the type of the current data collection node, and the preset node jump rules, determine the next data collection node for the current data collection node.

[0005] According to another aspect of this disclosure, an information collection device is provided, comprising: The request receiving unit is configured to receive user requests for information collection tasks; A step tree determination unit is configured to determine a step tree pre-configured for the information collection task, the step tree including multiple collection nodes, each collection node being associated with a collection problem in the information collection task; The data collection unit is configured to determine an initial data collection node, and starting from the initial data collection node, perform the data collection process iteratively until a preset termination condition is met. Each iteration includes: generating and returning a corresponding data collection question to the user based on the current data collection node; obtaining the user's answer to the data collection question; and determining the next data collection node based on the answer information, the type of the current data collection node, and a preset node jump rule.

[0006] This disclosure pre-configures a step tree corresponding to the information collection task and iteratively collects data starting from the initial collection node until a preset termination condition is met. In each iteration, the next collection node is dynamically determined based on the type of the current collection node, preset node jump rules, and the user's answer to the collection question corresponding to the current collection node. This allows the collection path to be adjusted in real time according to the user's answer information. This method can effectively avoid redundant questioning caused by fixed-sequence collection and significantly improve the efficiency and accuracy of information collection.

[0007] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0008] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure.

[0009] Figure 1 This is a flowchart of the information collection method provided in this public disclosure.

[0010] Figure 2 This is a schematic diagram of the step tree provided in this disclosure.

[0011] Figure 3 This is a schematic block diagram of the information collection device disclosed herein.

[0012] Figure 4 This is a block diagram of an electronic device used to implement the information acquisition method of the embodiments of this disclosure. Detailed Implementation

[0013] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0014] In related technologies, information collection often relies on pre-programmed linear dialogue scripts or simple rule branches. In linear dialogue scripts, the collection path follows a fixed, predetermined order. Regardless of the user's answers, the process proceeds step-by-step according to the established questionnaire, making it impossible to skip irrelevant questions or delve deeper into key information, resulting in numerous redundant interactions and low efficiency. While simple rule branches introduce conditional jumps, the branch logic is hard-coded at the code level. Adding or removing nodes, adjusting the order, or changing conditions all require direct modification of the source code, leading to poor scalability.

[0015] In view of this, the present disclosure provides an information collection method. This information collection method can be implemented by an application on a smart terminal or at least by a smart terminal that integrates information collection functionality. The smart terminal can be a smart notebook, mobile phone, tablet computer, personal computer, or wearable smart device, etc.

[0016] Figure 1 A flowchart of the information collection method provided in the embodiments of this disclosure is shown below. Figure 1 As shown, the method may include the following steps: Step 101: Receive the user's request for the information collection task.

[0017] Step 102: Determine the step tree pre-configured for the information collection task. The step tree includes multiple collection nodes, and each collection node is associated with a collection question in the information collection task.

[0018] Step 103: Determine the initial collection node. Starting from the initial collection node, execute the collection process iteratively until the preset termination condition is met. Each iteration includes: generating and returning the corresponding collection question to the user based on the current collection node; obtaining the user's answer to the collection question; and determining the next collection node based on the answer, the type of the current collection node, and the preset node jump rules.

[0019] As can be seen from the above process, this disclosure pre-configures a step tree corresponding to the information collection task and iteratively collects data starting from the initial collection node until a preset termination condition is met. In each iteration, the next collection node is dynamically determined based on the type of the current collection node, the preset node jump rules, and the user's answer to the collection question corresponding to the current collection node. This enables the collection path to be adjusted in real time according to the user's answer information. This method can effectively avoid redundant questioning caused by fixed-sequence collection and significantly improve the efficiency and accuracy of information collection.

[0020] The following describes in detail each step of the above process and the effects that can be further produced, with reference to the embodiments.

[0021] First, the above step 101, namely "receiving a user's request for an information collection task", will be described in detail with reference to the embodiments.

[0022] In the embodiments of this disclosure, a user's request for an information collection task can be triggered by an intelligent agent, and can include the following two triggering methods: Active triggering: Users can directly invoke information collection functions by explicitly interacting with preset interactive elements in the application's front-end interface provided by the intelligent agent, thereby generating and sending collection requests. For example, in the main interface of a postgraduate entrance examination information intelligent agent, there is a function entry point for "one-click generation of postgraduate entrance examination plan". After the user clicks on this function entry point, the intelligent agent generates a collection request and sends it to the backend server, triggering the subsequent information collection process.

[0023] Implicit Triggering: In natural language conversations between users and the agent, without the user needing to explicitly invoke functions, the agent uses natural language understanding technology to interpret the user's intent. When it autonomously determines that the user has an information collection need, the agent automatically initiates a collection request. For example, if a user mentions "help me choose a school" in a chat with the agent, after receiving this statement, the agent performs semantic analysis, extracts the need for "choosing a graduate school," and determines that the fulfillment of this need depends on the collection of school recommendation information. The agent then automatically triggers the school recommendation information collection process.

[0024] Upon receiving a data collection request triggered by any of the above methods, the agent's backend server initiates the subsequent data collection process based on the request.

[0025] The following describes step 102, namely "determining a pre-configured step tree for the information collection task, the step tree including multiple collection nodes, each collection node being associated with a collection problem in the information collection task", in conjunction with an embodiment.

[0026] In the embodiments of this disclosure, a corresponding step tree is pre-configured for each information collection task. The step tree includes multiple collection nodes, and each collection node is associated with a collection problem in the information collection task.

[0027] like Figure 2 The diagram shown is a schematic of the step tree provided in this disclosure. The step tree includes 10 nodes, which are arranged in a functional hierarchy as the root node (node ​​1), leaf nodes (nodes 3, 4, 6, 8, 9 and 10), and internal nodes (nodes 2, 5 and 7). The acquisition path from the root node to any leaf node constitutes a complete acquisition sequence.

[0028] Based on the logical relationships between the data collection issues, the data collection nodes include at least two types to enable flexible path control.

[0029] A fixed-route node, associated with a single child node. The collection question associated with this type of node has a simple linear relationship with subsequent questions. Structurally, it can contain a specific `next_node_id` field, pointing to a unique next node. Regardless of the user's answer to the question at this node, the process will always redirect to this specified node. For example... Figure 2 In this context, the jump from node 1 to node 5 can be set as a fixed jump.

[0030] Conditional redirection nodes are associated with multiple child nodes. The data collection question associated with this type of node is a branch point in its subsequent process; triggering the next question depends on the user's answer. The system will dynamically evaluate which branch's conditions are met based on the user's answer, thereby determining the redirection path. For example... Figure 2 In the process, depending on the user's answer, node 7 may redirect to node 8, node 9, or node 10.

[0031] In practical applications, the aforementioned step tree can be set up as a configurable resource decoupled from business logic in the plug-in scheduling layer of a general information collection system. Specifically, for each intelligent agent application, when a user triggers an information collection task through the front-end page of the intelligent agent application, the pre-configured step tree is called from the plug-in scheduling layer, and the collection task is executed based on the step tree.

[0032] The following describes in detail step 103, namely, "determine the initial acquisition node, take the initial acquisition node as the starting point, and execute the acquisition process in an iterative manner until the preset termination condition is met," with reference to the embodiments.

[0033] After determining the pre-configured step tree for the information collection task, the first step is to determine the initial collection node.

[0034] In one embodiment, the received user request for an information collection task carries a task identifier for that task. Based on this task identifier, it is determined whether the information collection task contains historical collection data and a corresponding interruption node identifier. Specifically, the task identifier can be used as an index to query a database (such as a cache database Redis or a relational database MySQL) to see if it stores historical collection data and a corresponding interruption node identifier for that task identifier.

[0035] The interruption node identifier refers to the identifier of the currently processing data collection node that is recorded in real time when the information collection task is interrupted due to reasons such as user-initiated pause, network anomaly, or session timeout. During the data collection process, once an interruption trigger condition is detected, the identifier of the current data collection node, along with the task identifier and the historical data already obtained, is associated and stored in the database. This serves as the basis for resuming the information collection task and ensures that the progress before the interruption can be directly located when data collection resumes.

[0036] When no historical data corresponding to the task identifier exists in the database, it indicates that this is a completely new information collection task. In this case, the root node of the step tree (e.g., Figure 2 Node 1) serves as the starting point of the data collection process, returning the data collection question corresponding to the root node to the user.

[0037] If the database contains historical data and interruption node identifiers corresponding to the task identifier, it indicates that the information collection task has not been completed due to session interruption or other reasons and needs to be resumed. In this case, the node corresponding to the interruption node identifier (such as...) can be retrieved. Figure 2 Node 5) is directly identified as the initial collection node, and the interruption node identifier is returned to the user. The collection question corresponding to the corresponding node is returned, so that the user does not need to answer the question that has already been answered.

[0038] By including a task identifier in the request and intelligently determining the historical status of the information collection task based on this identifier, the initial collection node can be determined according to different scenarios. This mechanism enables breakpoint continuation of the collection process, avoids users repeatedly answering questions about already collected information, reduces redundant operations, and ensures the continuity and integrity of collected data, thereby improving the efficiency of information collection and the user experience.

[0039] Once the initial acquisition node is determined, the acquisition process is executed iteratively from this initial acquisition node until the preset termination condition is met.

[0040] The preset termination condition includes at least one of the following: The next data collection node cannot be determined. Specifically, this can include the following two situations: First, the current data collection node is not associated with any child nodes, such as when the current data collection node is a leaf node in the step tree, which is not associated with any child nodes; second, when the current data collection node is a conditional jump node, none of its associated child nodes meet the corresponding triggering rules.

[0041] The data acquisition process reaches a preset maximum number of iterations to prevent infinite looping due to logical configuration errors.

[0042] By constructing the aforementioned data collection process termination mechanism, we can avoid process stagnation due to the lack of subsequent nodes, prevent the waste of system resources caused by unlimited iteration, and ensure the orderliness and stability of the information collection process.

[0043] Each iteration can include the following steps: Based on the current data collection node, generate and return the corresponding data collection question to the user.

[0044] Obtain user responses to the collected questions; Based on the response information, the type of the current data collection node, and the preset node jump rules, determine the next data collection node for the current data collection node.

[0045] Specifically, if the current data collection node is a fixed jump node, then the single child node associated with the current data collection node will be designated as the next data collection node. For example, if the current data collection node is... Figure 2 Node 2 in the data collection is configured as a fixed jump node. No matter how the user answers the corresponding data collection question, the next data collection node will always be node 5.

[0046] If the current collection node is a conditional jump node, the next collection node is determined from multiple child nodes associated with the current collection node based on the full response information of the information collection task. The full response information is a cumulative contextual information, which includes not only the response information corresponding to the current collection node, but also the historical response information obtained before this response information.

[0047] The above approach not only ensures the execution efficiency of fixed-process data collection tasks, but also meets the requirement of dynamic adaptation of data collection paths based on the full range of user responses in complex scenarios.

[0048] Based on the full response information of the information collection task, when determining the next collection node from multiple child nodes associated with the current collection node, the full response information is first parsed to obtain key information, such as the user's selected option value, the entered numerical value, and keywords in the text. Then, for each child node associated with the current collection node, based on the extracted key information, it is determined whether the child node meets the corresponding triggering rule. This evaluation is performed according to a preset order (such as the node configuration order) of the multiple child nodes associated with the current collection node, and the first child node that meets the triggering rule is determined as the next collection node.

[0049] The above method can avoid traversing invalid nodes or irrelevant paths, thereby improving the accuracy and efficiency of information collection.

[0050] Based on key information, determining whether a child node meets the corresponding triggering rule can specifically include: Based on key information, calculate the truth value of each condition item in the triggering rule corresponding to the child node; The default expression engine (such as Java Expression Language (JEXL)) is invoked to perform logical operations on the truth values ​​of each condition item to obtain the triggering result of the triggering rule; If the trigger result is true, then the child node satisfies the corresponding trigger rule; otherwise, the child node does not satisfy the corresponding trigger rule.

[0051] By introducing an expression engine for rule calculation, complex and multi-condition logical judgments can be achieved, thereby avoiding the errors and limitations caused by manual judgment or simple hard-coded logic, and thus improving the accuracy of node jumps in complex condition scenarios.

[0052] The full set of answer information can be obtained in the following way: retrieve all historical answer information under the information collection task from the cache database (such as Redis), and then merge it with the answer information obtained in the current iteration to obtain the full set of answer information.

[0053] Caching mechanisms can improve the efficiency of reading historical data, avoid the performance overhead of directly accessing the main database in each iteration, and ensure the continuity and consistency of data during the collection session.

[0054] In addition, when the data collection process terminates due to the above termination conditions, all the "collection question-answer information" pairs collected in this data collection task will be standardized and encapsulated, and output as a complete structured data (such as a JSON object), thus completing the process from interactive data collection to structured data delivery.

[0055] It should also be noted that, in the embodiments of this disclosure, the answer information during the collection process is stored in a cache database and a main database. The cache database stores all the questions and answers asked by the user in this information collection task. Each time information is stored, existing answer information is read first, then the new answer information is merged with the existing answer information before being stored in the cache database. The main database only needs to store the questions and corresponding answer information from each iteration.

[0056] The collection, storage, use, processing, transmission, provision, and disclosure of any type of information, such as user personal information, in this technical solution comply with relevant laws and regulations and do not violate public order and good morals.

[0057] The foregoing has described specific embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0058] According to another embodiment, an information collection device is provided. Figure 3 A schematic block diagram of the information collection device according to one embodiment is shown. Figure 3 As shown, the device 300 includes a request receiving unit 301, a step tree determination unit 302, and a data acquisition unit 303. The main functions of each component are as follows: The request receiving unit 301 is configured to receive user requests for information collection tasks; Step tree determination unit 302 is configured to determine a step tree pre-configured for the information collection task, the step tree including multiple collection nodes, each collection node being associated with a collection problem in the information collection task; The acquisition unit 303 is configured to determine an initial acquisition node, and starting from the initial acquisition node, perform the acquisition process iteratively until a preset termination condition is met. Each iteration includes: generating and returning a corresponding acquisition question to the user based on the current acquisition node; obtaining the user's answer to the acquisition question; and determining the next acquisition node of the current acquisition node according to the answer information, the type of the current acquisition node, and a preset node jump rule.

[0059] The types of the acquisition nodes include at least fixed jump nodes and conditional jump nodes. The fixed jump node is associated with a single child node, and the conditional jump node is associated with multiple child nodes. The acquisition unit 303 is specifically configured as follows: When the current acquisition node is a fixed jump node, the single child node associated with the current acquisition node is determined as the next acquisition node; When the current collection node is a conditional jump node, the next collection node is determined from multiple child nodes associated with the current collection node based on the full response information of the information collection task; wherein, the full response information includes the response information and historical response information obtained before the response information.

[0060] Specifically, the acquisition unit 303 is configured as follows: The full response information is parsed to obtain key information from the full response information; For each child node associated with the current collection node, based on the key information, determine whether the child node meets the corresponding triggering rule; The first child node that meets the triggering rule is determined as the next data collection node.

[0061] Specifically, the acquisition unit 303 is configured as follows: Based on the key information, calculate the truth value of each condition item in the triggering rule corresponding to the child node; The preset expression engine is invoked to perform logical operations on the truth values ​​of each condition item to obtain the triggering result of the triggering rule; If the triggering result is true, then the child node satisfies the corresponding triggering rule; otherwise, the child node does not satisfy the corresponding triggering rule.

[0062] Specifically, the acquisition unit 303 is configured as follows: The historical answer information is retrieved from the cache database, and the answer information and the historical answer information are merged to obtain the full answer information; Based on the full response information, the next collection node is determined from the multiple child nodes associated with the current collection node.

[0063] The request carries the task identifier of the information collection task; The step tree determination unit 302 is specifically configured as follows: Based on the task identifier, determine whether the information collection task has historical collection data and corresponding interruption node identifiers; If the historical data is not available, the root node of the step tree is determined as the initial data collection node. When the historical data exists, the node corresponding to the interrupted node identifier is determined as the initial data collection node.

[0064] The device 300 also includes: The output unit 304 is configured to convert each of the answer information acquired during the acquisition process and its associated acquisition question into structured data and output it when the acquisition process terminates.

[0065] The preset termination condition includes at least one of the following: Unable to determine the next data collection node; The data acquisition process reaches the preset maximum number of iterations.

[0066] The inability to determine the next data collection node includes: The current collection node is not associated with any child nodes, or when the current collection node is a conditional jump node, none of its associated child nodes meet the corresponding triggering rules.

[0067] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0068] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0069] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 402 or a computer program loaded from storage unit 408 into random access memory (RAM) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0070] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0071] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose 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 401 performs the various methods and processes described above, such as information acquisition methods. For example, in some embodiments, the information acquisition method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the content recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform a medical report interpretation method by any other suitable means (e.g., by means of firmware).

[0072] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0073] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This 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 when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0074] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0075] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0076] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0077] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0078] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0079] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An information collection method, comprising: Receive user requests for information collection tasks; A step tree pre-configured for the information collection task is determined, the step tree including multiple collection nodes, each collection node being associated with a collection question in the information collection task; Determine the initial acquisition node, and use the initial acquisition node as the starting point to perform the acquisition process in an iterative manner until the preset termination condition is met; Each iteration includes: Based on the current data collection node, generate and return the corresponding data collection question to the user; Obtain the user's answer information to the collected questions; Based on the response information, the type of the current data collection node, and the preset node jump rules, determine the next data collection node for the current data collection node.

2. The method according to claim 1, wherein, The types of the acquisition nodes include at least fixed jump nodes and conditional jump nodes. The fixed jump node is associated with a single child node, and the conditional jump node is associated with multiple child nodes. The step of determining the next collection node for the current collection node based on the response information, the type of the current collection node, and preset node jump rules includes: When the current acquisition node is a fixed jump node, the single child node associated with the current acquisition node is determined as the next acquisition node; When the current collection node is a conditional jump node, the next collection node is determined from multiple child nodes associated with the current collection node based on the full response information of the information collection task; wherein, the full response information includes the response information and historical response information obtained before the response information.

3. The method according to claim 2, wherein, The process of determining the next collection node from multiple child nodes associated with the current collection node based on the full response information of the information collection task includes: The full response information is parsed to obtain key information from the full response information; For each child node associated with the current collection node, based on the key information, determine whether the child node meets the corresponding triggering rule; The first child node that meets the triggering rule is determined as the next data collection node.

4. The method according to claim 3, wherein, The step of determining whether the child node meets the corresponding triggering rule based on the key information includes: Based on the key information, calculate the truth value of each condition item in the triggering rule corresponding to the child node; The preset expression engine is invoked to perform logical operations on the truth values ​​of each condition item to obtain the triggering result of the triggering rule; If the triggering result is true, then the child node satisfies the corresponding triggering rule; otherwise, the child node does not satisfy the corresponding triggering rule.

5. The method according to claim 2, wherein, The process of determining the next collection node from multiple child nodes associated with the current collection node based on the full response information of the information collection task includes: The historical answer information is retrieved from the cache database, and the answer information and the historical answer information are merged to obtain the full answer information; Based on the full response information, the next collection node is determined from the multiple child nodes associated with the current collection node.

6. The method according to claim 1, wherein, The request carries the task identifier of the information collection task; The determination of the initial acquisition node includes: Based on the task identifier, determine whether the information collection task has historical collection data and corresponding interruption node identifiers; If the historical data is not available, the root node of the step tree is determined as the initial data collection node. When the historical data exists, the node corresponding to the interrupted node identifier is determined as the initial data collection node.

7. The method according to claim 1, further comprising: When the collection process is terminated, each of the answers obtained during the collection process and its associated collection questions are converted into structured data and output.

8. The method according to claim 2, wherein, The preset termination condition includes at least one of the following: Unable to determine the next data collection node; The data acquisition process reaches the preset maximum number of iterations.

9. The method according to claim 8, wherein, The inability to determine the next data collection node includes: The current collection node is not associated with any child nodes, or when the current collection node is a conditional jump node, none of its associated child nodes meet the corresponding triggering rules.

10. An information acquisition device, comprising: The request receiving unit is configured to receive user requests for information collection tasks; A step tree determination unit is configured to determine a step tree pre-configured for the information collection task, the step tree including multiple collection nodes, each collection node being associated with a collection problem in the information collection task; The acquisition unit is configured to determine an initial acquisition node, and starting from the initial acquisition node, execute the acquisition process in an iterative manner until a preset termination condition is met. Each iteration includes: generating and returning a corresponding collection question to the user based on the current collection node; obtaining the user's answer to the collection question; and determining the next collection node for the current collection node based on the answer, the type of the current collection node, and preset node jump rules.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-9.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-9.

Images