Information collection method, device and computer equipment combining RPA and AI

Abstract

The present application proposes an information collection method combining RPA and AI, which relates to the fields of artificial intelligence (AI) and robotic process automation (RPA), wherein the method includes: establishing a dialogue with the target object and interacting with it to obtain target information based on the contact information of the target object, querying the reference information of the target object from a reference database, verifying the target information based on the reference information, and if the verification passes, entering the target information of the target object into the target system based on the robotic process automation RPA. In the present application, a dialogue is established with the target object to automatically obtain the target information, and when the target information is verified based on the reference information, the target information is stored, thereby improving the efficiency and reliability of obtaining the target information and reducing the cost.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence (AI) and robotic process automation (RPA), and in particular to an information collection method, apparatus, and computer equipment that combine RPA and AI. Background Art

[0002] The "One Standard, Three Realities" initiative, spearheaded by public security departments, standardizes standard addresses and enters detailed information about population, housing, and businesses into information systems, enabling information sharing and interoperability to provide information support for government policy. The collection and entry of basic information for this initiative is a key measure to advance the informatization of public security work. The nationwide "One Standard, Three Realities" data collection, encompassing standard addresses, actual resident population, actual housing, and actual business units, is essentially centered around the relatively fixed carrier of actual housing, with standard addresses as the foundation. The "Three Realities" information must be entered into the standard addresses.

[0003] However, during the actual collection process, relevant personnel need to go deep into the field to collect information. Users may not be at home or are busy and uncooperative, which brings great difficulties to the information collection work. At the same time, after the information is collected, the accuracy of the information cannot achieve the expected results. Summary of the Invention

[0004] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0005] To this end, this application proposes an information collection method, device and computer equipment that combines RPA and AI to improve the efficiency of information collection and reduce costs.

[0006] The first embodiment of the present application proposes an information collection method combining RPA and AI, including:

[0007] Establishing a dialogue with the target object and interacting with the target object to obtain target information according to the contact information of the target object;

[0008] Querying reference information of the target object from a reference database;

[0009] Verifying the target information according to the reference information;

[0010] If the verification passes, the target information of the target object is entered into the target system based on robotic process automation (RPA).

[0011] The second embodiment of the present application proposes an information collection device that combines RPA and AI, including:

[0012] An acquisition module is used to establish a dialogue with the target object and interact with the target object to obtain target information according to the contact information of the target object;

[0013] A query module, configured to query reference information of the target object from a reference database;

[0014] A verification module, configured to verify the target information based on the reference information;

[0015] The processing module is configured to enter the target information of the target object into the target system based on robotic process automation (RPA) if the verification passes.

[0016] The third aspect of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in the first aspect is implemented.

[0017] The third aspect of the present application provides a non-temporary computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method described in the first aspect is implemented.

[0018] The technical solution provided by the embodiments of the present application has the following beneficial effects:

[0019] Based on the target object's contact information, a dialogue is established with the target object and the target information is obtained through interaction. The target object's reference information is retrieved from the reference database. The target information is verified based on the reference information. If the verification passes, the target information of the target object is entered into the target system based on the Robotic Process Automation (RPA). In this application, a dialogue is established with the target object to automatically obtain the target information. When the target information passes the verification based on the reference information, the target information is stored, which improves the efficiency and reliability of target information acquisition and reduces costs.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 A flowchart of an information collection method combining RPA and AI provided in an embodiment of the present application;

[0023] Figure 2 A schematic diagram of address information verification provided for the implementation of this application;

[0024] Figure 3 A flowchart of another information collection method combining RPA and AI provided in an embodiment of the present application;

[0025] Figure 4 A schematic diagram of a voice dialogue provided in an embodiment of the present application;

[0026] Figure 5 A flowchart of another information collection method combining RPA and AI provided in an embodiment of the present application;

[0027] Figure 6 A framework flow chart for obtaining reference information provided in an embodiment of the present application;

[0028] Figure 7 A schematic diagram of a scenario for information collection combining RPA and AI, provided in an embodiment of the present application;

[0029] Figure 8 This is a schematic diagram of the structure of an information collection device combining RPA and AI provided in an embodiment of the present application;

[0030] Figure 9 A block diagram of an exemplary computer device suitable for implementing embodiments of the present application is shown. DETAILED DESCRIPTION

[0031] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0032] The following describes the information collection method, apparatus, and computer device combining RPA and AI in accordance with an embodiment of the present application with reference to the accompanying drawings.

[0033] Figure 1 A flowchart of an information collection method combining RPA and AI provided in an embodiment of the present application.

[0034] like Figure 1 As shown, the method includes the following steps:

[0035] Step 101: establish a dialogue with the target object and interact with the target object according to the contact information of the target object to obtain target information.

[0036] The target object refers to the object whose information needs to be collected.

[0037] Robotic process automation (RPA) uses specialized "robot software" to simulate human operations on computers, automatically executing process tasks according to rules. With the continuous development of artificial intelligence (AI), the application scope of robots is expanding. Interactive intelligent robots can be used for human-computer dialogue, implementing interactive services such as chatbots and intelligent customer service. In this embodiment, the target information is obtained through interaction.

[0038] In one implementation of this embodiment, a voice dialogue is established with the target object based on the target object's contact information, and questions are asked to the target object in the dialogue based on the attribute items that the target object is missing. Based on natural language processing (NPL), target information semantically related to the missing attribute items is extracted from the target object's response to the questions.

[0039] In another implementation of this embodiment, a conversation in the form of short messages is established with the target object based on the target object's contact information, and questions are asked to the target object in the conversation based on the attribute items that the target object is missing. Based on natural language processing NPL, target information semantically related to the missing attribute items is extracted from the target object's reply to the question.

[0040] For example, if the target object's missing attribute is its office address, a response containing the target object's office address is obtained from the target object via a voice conversation or short message. Then, based on natural language processing (NPL), the target information of the target object's office address is extracted from the response. The target object is not limited to one missing attribute; the principles for obtaining other missing attribute items are the same and are not limited in this embodiment.

[0041] It should be noted that the attribute items can be pre-set according to the needs of the collection scenario. For example, in the one-standard and three-real information collection, the attribute items include administrative divisions, addresses, personnel, and work units.

[0042] In one implementation of this embodiment, data cleaning, splitting, and fusion are performed on the acquired target information to improve the accuracy of the target information.

[0043] Step 102: Query reference information of the target object from a reference database.

[0044] The reference database refers to a database containing various information about the target object. For example, in the express delivery industry, since the detailed address of the recipient is required, the reference information of the target object can be found in the express delivery database. For example, if the target object is Zhang San, the reference information of Zhang Dan in the express delivery database may include:

[0045] Contact: Zhang San;

[0046] City: XX City;

[0047] District: New City District;

[0048] Street: Xinyakou Street;

[0049] Address: No. 206, Chunfeng Road;

[0050] Office address: XXX Company.

[0051] It should be noted that the reference database may also be other databases specifically used to collect statistics on relevant reference information of target objects, which is not limited in this embodiment.

[0052] Step 103: Verify the target information based on the reference information.

[0053] In one implementation of this embodiment, the reference information and the target information are input into a trained verification model based on NLP technology to determine whether the collected target information is consistent with the reference information.

[0054] In this embodiment, the target information is taken as an example for description. Figure 2 As shown, the same address is described in the address information, but the expression of the address description information is different, and there are differences between Chinese characters and numbers in the description. Therefore, when the trained verification model verifies the address information, it has learned the correspondence between the Chinese character description and the number description, and the correspondence between the amount of description information and the standard address. Therefore, according to the trained verification model, whether the target information is consistent with the reference information can be accurately identified.

[0055] In step 104 , if the verification passes, the target information of the target object is entered into the target system based on the Robotic Process Automation (RPA).

[0056] In this embodiment, after the collected target information is verified, the target information of the target object is entered into the target system based on robotic process automation (RPA). The target systems include the public security agency's permanent population system, the public security agency's floating population system, the police integrated platform system, the civil affairs system, the industrial and commercial system, the education system, the social security system, etc., which are not listed one by one in this embodiment.

[0057] As one implementation method, the target information of the target object can be automatically triggered to be entered into the target system based on Robotic Process Automation (RPA). As a second implementation method, the target information of the target object can be manually triggered to be entered into the target system based on Robotic Process Automation (RPA), so as to apply the collected information to actual business scenarios.

[0058] In the information collection method combining RPA and AI in this embodiment, a dialogue is established with the target object based on the target object's contact information, and the target information is obtained through interaction. The reference information of the target object is queried from a reference database, and the target information is verified based on the reference information. If the verification passes, the target information of the target object is entered into the target system based on the robotic process automation (RPA). In this application, a dialogue is established with the target object to automatically obtain the target information, and the target information is stored when the target information passes the verification based on the reference information. This improves the efficiency and reliability of target information acquisition while reducing the collection cost.

[0059] Based on the previous embodiment, this embodiment provides another information collection method that combines RPA and AI, illustrating how to obtain target information by establishing a voice dialogue. Figure 3 A flowchart of another information collection method combining RPA and AI provided in an embodiment of the present application.

[0060] like Figure 3 As shown, step 101 may include the following steps:

[0061] Step 301: Establish a voice dialogue with the target object based on the target object's contact information.

[0062] The contact information of the target object may be the contact information of an existing instant messaging application, such as WeChat, QQ, etc., or a dedicated application released by an information collection agency, which are not listed here one by one.

[0063] Step 302: Ask questions to the target object in the dialogue based on the attribute items that the target object is missing.

[0064] like Figure 4 As shown, Figure 4 A schematic diagram of a voice dialogue provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, based on Robotic Process Automation (RPA), a voice dialogue is automatically established with the target object, and the target information is obtained through at least one round of interactive dialogue.

[0065] Different target objects correspond to different missing attribute items, and the number of missing attribute items also varies.

[0066] Step 303 : Based on natural language processing (NPL), target information semantically related to the missing attribute item is extracted from the target object's response to the question.

[0067] As an implementation method, an extraction model trained based on natural language processing technology is used to perform semantic recognition on the target object's response to the question, so as to extract target information semantically related to the missing attribute items, thereby improving the efficiency of obtaining target information, avoiding the need for manpower to obtain target information, and reducing the acquisition cost.

[0068] Step 304: Using speech recognition technology, convert the target object's response from speech form into text form.

[0069] In one implementation of this embodiment, for ease of review, the target recipient's reply can be converted into corresponding text form using voice recognition technology and displayed for easy review and manual verification. It should be noted that in this scenario, step 304 can be performed simultaneously with step 303, or after step 303.

[0070] As another implementation, the target person's reply can be converted into a corresponding text form using speech recognition technology. This can then be used as input for an extraction model trained using natural language processing technology to improve the model's recognition efficiency. Furthermore, the converted text form can be displayed for easier viewing and understanding. It should be noted that in this scenario, step 304 is performed before step 303.

[0071] In the information collection method of this embodiment, by automatically establishing voice interaction with the target object, the target information of the target object can be automatically obtained without the need for personnel to collect the information on site. This avoids the high cost and difficulty of information collection caused by users being busy or not at home, improves the efficiency of information collection, and reduces the cost of information collection.

[0072] Based on the above embodiment, this embodiment provides another information collection method that combines RPA and AI. Figure 5 A flowchart of another information collection method combining RPA and AI provided in an embodiment of the present application.

[0073] like Figure 5 As shown, step 102 includes the following steps:

[0074] Step 501: Use the contact information and / or identification of the target object to search in a reference database to obtain original information.

[0075] The identifier is used to uniquely identify the target object, such as a telephone number, an ID number, etc. As an implementation method, the identifier can be obtained during the process of establishing a dialogue interaction with the target object.

[0076] In this embodiment, the reference database is taken as the express coefficient database as an example, combined with Figure 6The framework flowchart for obtaining reference information is explained below.

[0077] In this embodiment, the target object's contact information and / or identifier is stored in the express delivery system database. A pre-trained neural network model, such as a BERT model, is used to retrieve the target object's original information based on the target object's contact information and / or identifier. The original information includes the target object's matching contact name and contact number, the target object's administrative division, and one or more of the target object's workplaces. Administrative divisions include at least cities, districts, and streets.

[0078] Step 502: Segment the original information to obtain multiple second candidate words.

[0079] Step 503: Determine reference information semantically related to the set attribute item based on the plurality of second candidate words.

[0080] In one scenario of this embodiment, the set attribute items include contact person, city, district, street, detailed address and workplace.

[0081] For example, the original information is: No. 303, XX Road, Xinyakou Street, Xincheng District, Dongzhou City, received by Zhang San. The multiple second candidate words obtained through word segmentation are: Dongzhou City, Xincheng District, No. 303, XX Road, Zhang San.

[0082] Therefore, the reference information related to the semantics of the set attribute item is:

[0083] Contact: Zhang San;

[0084] City: Dongzhou City;

[0085] District: New City District;

[0086] Street: Xinyakou Street;

[0087] Address: No. 303, Moumou Road.

[0088] Workplace: None

[0089] Step 504: If there is a target attribute item whose reference information is not identified among the multiple set attribute items, query the database associated with the target attribute item based on the identified reference information to obtain the reference information of the target attribute item.

[0090] In this embodiment, if the reference information of the "work unit" in the set attribute item is not identified, the database associated with the target attribute item of "work unit" is queried based on the identified reference information to obtain the reference information of the target attribute item, and the work unit is identified as: Xincheng District Traffic Detachment.

[0091] In one implementation of this embodiment, in order to improve the accuracy of the determined reference information, after the work unit is identified, the entity name of the work unit in the relevant administrative department can be obtained to correct the reference information corresponding to the identified work unit: New City District Traffic Detachment, so as to improve the accuracy of the reference information determination of the target attribute item.

[0092] In the information collection method combining RPA and AI in this embodiment, reference information of the target object is obtained by querying from a reference database, and the target information is verified based on the reference information, thereby improving the efficiency and reliability of obtaining the target information and reducing the collection cost.

[0093] Based on the above embodiments, in order to improve the accuracy of determining the reference information related to the set attribute items, when the set attribute items include administrative divisions, after determining the reference information related to the semantics of the administrative divisions, the reference information corresponding to the administrative divisions can also be corrected according to the hierarchical relationship of the set standard administrative divisions. As an implementation method, the hierarchical relationship of the standard administrative divisions set by the relevant competent departments can be obtained, and the determined reference information can be corrected to improve the reliability of the reference information determination.

[0094] Based on the above embodiments, Figure 7 A schematic diagram of a scenario for information collection combining RPA and AI provided in an embodiment of the present application is shown as follows: Figure 7 As shown, the Robotic Process Automation (RPA) establishes a dialogue and interacts with the target subject based on their contact information to obtain target information. The target information includes one or more of household registration data, address data, population data, and housing data. After obtaining or capturing the target information, the data is sent to the RPA's intelligent verification module. After data cleaning, splitting, and fusing the target information, the module verifies the target information based on the obtained reference information. After successful verification, the target information is stored and automatically or manually triggered by the RPA process to enter the corresponding target information into the corresponding system. If the verification fails, the target information is placed in a pending verification library, requiring a new dialogue and interaction with the target subject to re-acquire the target information that failed verification.

[0095] It should be noted that the explanations of the aforementioned method embodiment are also applicable to this embodiment, and the principles are the same, so they will not be repeated in this embodiment.

[0096] In order to implement the above embodiments, the present application also proposes an information collection device that combines RPA and AI.

[0097] Figure 8 A schematic diagram of the structure of an information collection device combining RPA and AI provided in an embodiment of the present application.

[0098] like Figure 8 As shown, the device includes:

[0099] The acquisition module 81 is used to establish a dialogue with the target object and interact with the target object according to the contact information of the target object to obtain target information.

[0100] The query module 82 is configured to query the reference information of the target object from a reference database.

[0101] The verification module 83 is configured to verify the target information according to the reference information.

[0102] The processing module 84 is configured to enter the target information of the target object into the target system based on robotic process automation (RPA) if the verification passes.

[0103] Furthermore, in a possible implementation of the embodiment of the present application, the acquisition module 81 is configured to:

[0104] Establishing a voice or short message conversation with the target person based on the target person's contact information;

[0105] Asking questions to the target object in the conversation based on the attribute items missing from the target object;

[0106] Based on natural language processing (NPL), target information semantically related to the missing attribute item is extracted from the target object's response to the question.

[0107] In a possible implementation of the embodiment of the present application, the conversation is in voice form, and the apparatus further includes:

[0108] The speech recognition technology is used to convert the response of the target object from speech form to text form.

[0109] In a possible implementation of the embodiment of the present application, the acquisition module 81 is further configured to:

[0110] Segmenting the target object's response to the question based on the NPL to obtain a plurality of first candidate words;

[0111] Target information semantically related to the attribute item is determined based on the multiple first candidate words.

[0112] In a possible implementation of the embodiment of the present application, the query module 82 is configured to:

[0113] Using the contact information and / or identification of the target object, searching in the reference database to obtain original information;

[0114] Segmenting the original information to obtain a plurality of second candidate words;

[0115] The reference information semantically related to the set attribute item is determined based on the multiple second candidate words.

[0116] In a possible implementation of the embodiment of the present application, multiple attribute items are set.

[0117] The query module 82 is further configured to query a database associated with the target attribute item based on the identified reference information to obtain the reference information of the target attribute item if there is a target attribute item whose reference information has not been identified among the plurality of set attribute items.

[0118] In a possible implementation of the embodiment of the present application, the set attribute items include administrative divisions, and the query module 82 is further configured to:

[0119] According to the set hierarchical relationship of the standard administrative divisions, the reference information corresponding to the administrative divisions is modified.

[0120] In a possible implementation of the embodiment of the present application, the verification module 83 includes:

[0121] If the verification fails, a dialogue is re-established and interaction is performed with the target object to re-acquire the target information that failed the verification.

[0122] It should be noted that the above explanation of the method embodiment is also applicable to the device of this embodiment and will not be repeated here.

[0123] In the information collection device combining RPA and AI in this embodiment, a dialogue is established with the target object based on the target object's contact information, and the target information is obtained through interaction. The reference information of the target object is queried from a reference database, and the target information is verified based on the reference information. If the verification passes, the target information of the target object is entered into the target system based on the robotic process automation (RPA). In this application, a dialogue is established with the target object to automatically obtain the target information, and the target information is stored when the target information passes the verification based on the reference information. This improves the efficiency and reliability of target information acquisition while reducing the collection cost.

[0124] In order to implement the above embodiments, the embodiments of the present application also propose a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in the above method embodiments is implemented.

[0125] In order to implement the above embodiments, the embodiments of the present application further provide a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method described in the above method embodiments is implemented.

[0126] In order to implement the above embodiments, the embodiments of the present application further provide a computer program product, which, when an instruction processor in the computer program product executes, implements the method described in the above method embodiments.

[0127] Figure 9 A block diagram of an exemplary computer device suitable for implementing embodiments of the present application is shown. Figure 9 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0128] like Figure 9 As shown, computer device 12 is implemented as a general-purpose computing device. Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 that connects various system components (including memory 28 and processing unit 16).

[0129] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of such architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnection (PCI) bus.

[0130] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0131] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 9 Not shown, often called a "hard drive"). Although Figure 9 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a Compact Disc Read Only Memory (hereinafter referred to as: CD-ROM), a Digital Video Disc Read Only Memory (hereinafter referred to as: DVD-ROM), or other optical media) may be provided. In these cases, each drive can be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the various embodiments of the present application.

[0132] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally implement the functions and / or methods of the embodiments described herein.

[0133] The computer device 12 can also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). This communication can occur via an input / output (I / O) interface 22. Furthermore, the computer device 12 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via a bus 18. It should be understood that, although not shown, other hardware and / or software modules can be used in conjunction with the computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0134] The processing unit 16 executes various functional applications and data processing by running the programs stored in the memory 28 , such as implementing the methods mentioned in the above embodiments.

[0135] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0136] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0137] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0138] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0139] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0140] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0141] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0142] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. An information collection method combining RPA and AI, characterized in that: The method is applied in the collection of one-standard and three-real information, and includes the following steps: Establishing a dialogue with the target object and interacting with the target object according to the contact information of the target object to obtain target information, wherein the target information is address information, and the address information includes at least a city, a district, and a street; Querying reference information of the target object from a reference database, wherein the reference database is an express delivery database, and the reference information includes at least a city, a district, and a street; Verifying the target information using a verification model based on the reference information to determine whether the collected target information is consistent with the reference information; If the verification passes, the target information of the target object is entered into the target system based on the Robotic Process Automation (RPA); The querying of the reference information of the target object from the reference database includes: Using the contact information and / or identification of the target object, searching in the reference database to obtain original information; Segmenting the original information to obtain a plurality of second candidate words; Determining the reference information semantically related to the set attribute item according to the plurality of second candidate words; There are multiple attribute items set, and after determining the reference information semantically related to the set attribute items based on the multiple second candidate words, the method further includes: If there is a target attribute item whose reference information is not identified among the multiple set attribute items, a database associated with the target attribute item is queried based on the identified reference information to obtain the reference information of the target attribute item.

2. The method according to claim 1, characterized in that The step of establishing a dialogue with the target object and interacting with the target object to obtain target information based on the contact information of the target object includes: Establishing a voice or short message conversation with the target person based on the target person's contact information; Asking questions to the target object in the conversation based on the attribute items missing from the target object; Based on natural language processing (NPL), target information semantically related to the missing attribute item is extracted from the target object's response to the question.

3. The method according to claim 2, characterized in that The dialogue is based on speech, and the method further includes: The speech recognition technology is used to convert the response of the target object from speech form to text form.

4. The method according to claim 2, characterized in that The extracting target information semantically related to the missing attribute item from the target object's response to the question based on natural language processing (NPL) includes: Segmenting the target object's response to the question based on the NPL to obtain a plurality of first candidate words; According to the plurality of first candidate words, target information semantically related to the missing attribute item is determined.

5. The method according to claim 1, wherein The set attribute item includes an administrative division. After determining the reference information semantically related to the set attribute item based on the plurality of second candidate words, the method further includes: According to the set hierarchical relationship of the standard administrative divisions, the reference information corresponding to the administrative divisions is modified.

6. The method according to any one of claims 1 to 5, characterized in that Verifying the target information using a verification model according to the reference information includes: If the verification fails, a dialogue is re-established and interaction is performed with the target object to re-acquire the target information that failed the verification.

7. An information collection device combining RPA and AI, characterized in that: The device is applied in the collection of one-standard and three-real information, and includes the following steps: An acquisition module is used to establish a dialogue with the target object and interact with the target object to obtain target information based on the target object's contact information, wherein the target information is address information, and the address information includes at least a city, a district, and a street; A query module, configured to query reference information of the target object from a reference database, wherein the reference database is an express delivery database, and the reference information includes at least a city, a district, and a street; A verification module is used to verify the target information using a verification model based on the reference information to determine whether the collected target information is consistent with the reference information; A processing module, configured to enter the target information of the target object into a target system based on robotic process automation (RPA) if the verification passes; The query module is used to: Using the contact information and / or identification of the target object, searching in the reference database to obtain original information; Segmenting the original information to obtain a plurality of second candidate words; Determining the reference information semantically related to the set attribute item according to the plurality of second candidate words; There are multiple attribute items to be set. The query module is further configured to query a database associated with the target attribute item based on the identified reference information to obtain the reference information of the target attribute item if there is a target attribute item for which the reference information has not been identified among the plurality of set attribute items.

8. The device according to claim 7, characterized in that The acquisition module is used to: Establishing a voice or short message conversation with the target person based on the target person's contact information; Asking questions to the target object in the conversation based on the attribute items missing from the target object; Based on natural language processing (NPL), target information semantically related to the missing attribute item is extracted from the target object's response to the question.

9. The device according to claim 8, characterized in that The dialogue is based on speech, and the device further comprises: The speech recognition technology is used to convert the response of the target object from speech form to text form.

10. The device according to claim 8, characterized in that The acquisition module is further used to: Segmenting the target object's response to the question based on the NPL to obtain a plurality of first candidate words; According to the plurality of first candidate words, target information semantically related to the missing attribute item is determined.

11. The device according to claim 7, characterized in that The set attribute items include administrative divisions, query modules, and are also used for: According to the set hierarchical relationship of the standard administrative divisions, the reference information corresponding to the administrative divisions is modified.

12. The device according to any one of claims 7 to 11, characterized in that: The verification module includes: If the verification fails, a dialogue is re-established and interaction is performed with the target object to re-acquire the target information that failed the verification.

13. A computer device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

14. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images