Intelligent pushing method and device, storage medium and electronic equipment

Abstract

The invention provides an intelligent pushing method and device, a storage medium and electronic equipment. The method comprises the steps that a first number and user information corresponding to the first number are acquired; performing multi-level index operation based on the first number and a pre-constructed number database to obtain first attribution information; performing feature analysis based on the user information to determine user features, wherein the second attribution information is used for representing current location information of a user of the first number; and determining the push content of the first number based on the first attribution information and / or the second attribution information and / or the intention feature information, and performing information push based on the push content. Therefore, the pushing accuracy of the energy information preference can be improved by combining the first affiliation information, the second affiliation information and the intention, the number analysis efficiency can be improved by constructing the number database with the multi-level indexes, the occupied space can be reduced, the preference analysis efficiency is improved, and the system burden is reduced.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to an intelligent push method, device, storage medium and electronic device. Background Art

[0002] The energy management platform does not have a complete solution for user portraits of individual customers. In related technologies, user portraits are usually generated based on the user's single behavioral data. For example, only click situations are considered for analysis, which makes it difficult to quickly and fully mine user information for differentiated push notifications, resulting in the accuracy of user preference push notifications being affected. Energy information is closely related to many factors. Considering only single behavioral data makes the analysis of user preferences for energy data less accurate. The analysis of a large amount of data at one time is inefficient and may impose a heavy burden on the system. Therefore, the current energy management platform still has problems with low accuracy, low analysis efficiency, and a heavy system burden in pushing users' energy information preferences. Summary of the invention

[0003] The embodiments of the present application provide an intelligent push method, device, storage medium and electronic device, which can improve the accuracy and efficiency of pushing energy information preferences and reduce the system burden.

[0004] In a first aspect, an embodiment of the present application provides an intelligent push method, which is applied to a server of an energy management system, wherein the energy management system further includes an energy management platform and a first memory, wherein the first memory is provided with a pre-built number database, and the pre-built number database includes a multi-level index structure, and the method includes: Obtaining a first number and user information corresponding to the first number, wherein the first number is a number for triggering a refresh operation on content pushed by the energy management platform, the first number is bound to the energy management platform, and the user information includes operation information of the user of the first number on energy information of the energy management platform within a historical time period; Performing a multi-level indexing operation based on the first number and the pre-built number database to obtain first attribution information, where the first attribution information is the region information of the first number; Performing feature analysis based on the user information to determine user features, the user features including second attribution information and / or intention feature information, the second attribution information is used to represent the current location information of the user of the first number, and the intention feature information is used to represent the user's preference for push information; The push content of the first number is determined based on the first attribution information and / or the second attribution information and / or the intention characteristic information, and information is pushed based on the push content.

[0005] In a possible embodiment, the multi-level index structure of the pre-constructed number database includes a primary index area and a secondary index area, and the pre-constructed address database includes a header area, a record area, the secondary index area and the primary index area; the addresses of the header area, the record area, the secondary index area and the primary index area have an address association relationship, and the address association relationship includes a sequential continuation relationship; the record area is used to store resolution information data, the resolution information data represents at least one level of attribution region and operator information, and the resolution information data is variable-length data.

[0006] In a possible embodiment, performing a multi-level indexing operation based on the first number and the pre-built number database to obtain the first attribution information includes: Performing a data conversion operation on the first number to obtain standard number information; Determining address location information based on the standard number information; An indexing operation is performed based on the address location information and a binary indexing operation to determine the first attribution information.

[0007] In a possible embodiment, performing a data conversion operation on the first number to obtain standard number information includes: Determine a second number by intercepting the first number, wherein the number of characters included in the second number is less than or equal to the number of characters included in the first number; Performing a numerical type conversion operation based on the second number to obtain the standard number information, where the numerical type of the standard number information includes an integer type; The determining of the address location information based on the standard number information includes: The standard number information is subjected to an address association operation to determine the starting position information of the index, where the starting position information is the address in the secondary index area.

[0008] In a possible embodiment, the operation information includes selection information and / or information browsing time and / or input text information and / or feedback information, the feedback information is preference feedback information actively selected by the user, and the determining of user characteristics by performing feature analysis based on the user information includes: Determine the information intention parameter based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and a preset first impact factor set; Determine the intention characteristic information by sorting based on the information intention parameters; The second attribution information is determined by performing a feature extraction operation based on the selection information and / or the information browsing duration for the selection information and / or the feedback information for the selection information and / or the input text information.

[0009] In a possible embodiment, the energy management system further includes multiple energy sub-platforms, the user information includes first-category user information and / or second-category user information, the first-category user information is the operation information, and the second-category user information includes data information from multiple energy sub-platforms associated with the energy management platform; the information intention parameter determined based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and the preset multiple influencing factors includes: Determine energy demand information of the user of the first number based on the second type of user information, where the energy demand includes energy demand or energy consumption demand for new energy vehicles; The information intention parameter is determined based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and / or the energy demand information and a preset second influencing factor set.

[0010] In a possible embodiment, determining the push content of the first number based on the first attribution information and / or the second attribution information and / or the intention feature information includes: Determine a regional importance coefficient based on the first attribution information, the second attribution information and the user characteristics, wherein the regional importance coefficient is used to constrain a push content proportion coefficient for the first attribution information and the second attribution information; Push content with regional characteristics is determined based on the importance coefficient, the first attribution information, the second attribution information, and the intention characteristics.

[0011] In a second aspect, an embodiment of the present application provides an intelligent push device, which is applied to a server of an energy management system, wherein the energy management system further includes an energy management platform and a first memory, wherein the first memory is provided with a pre-built number database, wherein the pre-built number database includes a multi-level index structure, and the device includes: an acquisition module, configured to acquire a first number and user information corresponding to the first number, wherein the first number is a number for triggering a refresh operation on content pushed by the energy management platform, the first number is bound to the energy management platform, and the user information includes operation information of the user of the first number on energy information of the energy management platform within a historical time period; An indexing module, configured to perform a multi-level indexing operation based on the first number and the pre-built number database to obtain first attribution information, wherein the first attribution information is the region information of the first number; a feature determination module, configured to determine user features by performing feature analysis based on the user information, wherein the user features include second attribution information and / or intention feature information, wherein the second attribution information is used to represent the current location information of the user of the first number, and the intention feature information is used to represent the user's preference for push information; The content determination module is used to determine the push content of the first number based on the first attribution information and / or the second attribution information and / or the intention characteristic information, and push information based on the push content.

[0012] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes some or all of the steps described in the first aspect.

[0013] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a processor, a second memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the second memory and are configured to be executed by the processor, and the program includes instructions for executing some or all of the steps described in the first aspect of the embodiment of the present application.

[0014] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0015] By implementing the embodiment of the present application, a first number and user information corresponding to the first number are obtained, the first number is a number that triggers a refresh operation on the push content of the energy management platform, the first number has a binding relationship with the energy management platform, and the user information includes the operation information of the user of the first number on the energy information of the energy management platform in the historical time period; a multi-level index operation is performed based on the first number and the pre-constructed number database to obtain the first attribution information, the first attribution information is the regional information of the first number; based on the user information, a feature analysis is performed to determine the user characteristics, the user characteristics include the second attribution information and / or the intention feature information, the second attribution information is used to characterize the current location information of the user of the first number, and the intention feature information is used to characterize the user's preference for the push information; based on the first attribution information and / or the second attribution information and / or the intention feature information, the push content of the first number is determined, and information is pushed based on the push content. In this way, by combining the first attribution information, the second attribution information and the intention, the push accuracy of the energy information preference can be improved, and by constructing a number database with a multi-level index, the number resolution efficiency can be improved, and the occupied space can be reduced, thereby improving the efficiency of preference analysis and reducing the system burden. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0017] Figure 1 It is a schematic diagram of the architecture of an energy management system provided in an embodiment of the present application; Figure 2 This is a method flow chart of an intelligent push method provided by an embodiment of the present application; Figure 3 It is a structural diagram of a number database provided in an embodiment of the present application; Figure 4 This is a block diagram of the functional units of an intelligent push device proposed in an embodiment of the present application; Figure 5 This is a block diagram of the functional units of another intelligent push device provided in an embodiment of the present application; Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or electronic device that includes a series of steps or units is not limited to the listed steps or units, but in an optional example also includes steps or units that are not listed, or in an optional example also includes other steps or units inherent to these processes, methods, products, or electronic devices.

[0020] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] The intelligent push method, device, storage medium and electronic device provided in the embodiments of the present application can be applied to Figure 1 In the energy management system shown, see Figure 1 , Figure 1 It is a schematic diagram of the architecture of an energy management system provided in an embodiment of the present application. The energy management system 100 includes an energy management platform 110 , a server 120 and a first storage 130 . The energy management platform 110 can communicate with the server 120 .

[0022] In this solution, the energy management platform 110 can be accessed by users, and the energy management platform 110 can interact with the server 120 to obtain data information generated by other terminal devices for access, which can specifically be request information, view messages, gesture operation instructions, etc. The server 120 refers to a remote computer used to process a large number of computing tasks and perform analysis and processing. The first memory 130 is used to store data. In this solution, the first memory 130 is provided with a pre-built number database. In this solution, the server 120 is used to perform specific control and situation analysis of intelligent push.

[0023] Based on this, the present application provides an intelligent push method, device, storage medium and electronic device, and the present application is described in detail below in conjunction with the accompanying drawings.

[0024] See also Figure 2 , Figure 2 : is a method flow chart of an intelligent push method provided in an embodiment of the present application, the method is applied to a server of an energy management system, the energy management system also includes an energy management platform and a first memory, the first memory is provided with a pre-built number database, the pre-built number database includes a multi-level index structure, such as Figure 2 As shown, the method comprises the following steps: S210, obtaining a first number and user information corresponding to the first number, wherein the first number is a number for triggering a refresh operation on content pushed to the energy management platform, the first number has a binding relationship with the energy management platform, and the user information includes operation information of the user of the first number on the energy information of the energy management platform within a historical time period.

[0025] Among them, the first number is the number that triggers the refresh push content operation among multiple numbers bound to the energy management system, specifically a mobile phone number. In some cases, it can be other numbers, but the description content uses the mobile phone number as an example. Binding can be understood as using the number to register or use the platform; the historical time period is the time period before the current use time, and the user information is the operation information of the user of the first number on the energy management platform before the current time, which can specifically be the selection of push content, viewing time, active feedback willingness, input text information, etc. on the energy management platform, which is not limited here.

[0026] Among them, the user information can be empty, that is, if the user is using it for the first time, or the usage record of the historical time period is deleted in some way, such as logging out.

[0027] S220: Perform a multi-level indexing operation based on the first number and the pre-built number database to obtain first attribution information, where the first attribution information is the region information of the first number.

[0028] The pre-built number database is a database designed to make the system occupy less space and resolve faster. The pre-built number database includes a multi-level index structure, and the first attribution information is determined by performing a multi-level index operation on the first number through the pre-built number database. The first attribution information is the attribution region information corresponding to the first number. For example, the first number is a mobile phone number, and the number is resolved based on the mobile phone number to determine the region information of the mobile phone number.

[0029] In a possible embodiment, the multi-level index structure of the pre-constructed number database includes a primary index area and a secondary index area, and the pre-constructed address database includes a header area, a record area, the secondary index area and the primary index area; the addresses of the header area, the record area, the secondary index area and the primary index area have an address association relationship, and the address association relationship includes a sequential continuation relationship; the record area is used to store resolution information data, the resolution information data represents at least one level of attribution region and operator information, and the resolution information data is variable-length data.

[0030] Among them, the above-mentioned sequential extension relationship can mean that the storage addresses of the header area, record area, secondary index area and primary index area are arranged in order from small to large, and can be adjacent or have empty addresses between every two, which is not limited here.

[0031] For example, the standard length of a mobile phone number is 11 digits, divided into three sections: the first three digits are the Internet service provider (ISP), the 4th to 7th digits are the area code, and the 8th to 11th digits are the user number. The ISPs include China Mobile, China Unicom, China Telecom, China Broadcasting and Television, China Mobile Virtual, China Unicom Virtual, China Telecom Virtual, and China Broadcasting and Television Virtual, and the numbers assigned are 130-199. Area codes can only be accurate to the province and city.

[0032] Among them, see Figure 3 and Table 1, Figure 3It is a structural diagram of a number database provided by an embodiment of the present application. The format of the pre-built number database can refer to the following Table 1. Among them, the length of the header area is not fixed, which means that the size of the header area is not fixed and can vary according to specific needs and the amount of data stored. This provides flexibility for storing different types and quantities of information. For example, it can store a small amount of basic information or a large amount of detailed information without being restricted by length. Specifically, the header area is used to store file type, creation date, last modification date, file size, permission information, etc. When more metadata (such as file encryption information, owner information, backup information, etc.) needs to be stored, the header area can be expanded to accommodate these new contents. The specific data form is also not limited. The header area can store database version information (integer), database name (string), storage engine type (enumeration type or string), data encoding method (string), etc. The length of the record area is also variable and can be changed according to the main data of the record. The data stored in the record area can be regarded as an array, but the length of the array is not fixed. It can store various data elements, and the lengths of these elements can also be different. A fixed-length secondary index area means that the size of the area is fixed, and its length is determined when it is created. This helps improve the performance and stability of the system. Storing a fixed-length array means that the data elements in it have the same length and are stored in the form of an array. The length of the primary index area is not fixed, which means that its size can be adjusted according to the needs of the system. It may vary depending on the size of the stored data and the complexity of the structure. The stored data is a fixed-length array, which means that the data elements in the primary index area have the same length and data type and are stored in the form of an array.

[0033] Table 1

[0034] Specifically, the format of the header area can refer to the following Table 2. The checksum is a value calculated by a specific algorithm on the data, which is used to verify whether an error occurs during the transmission or storage of the data. The version number is used to identify the specific version followed by the data structure or the data it contains. This 4-byte version number allows the system to clearly understand the format, functional characteristics and compatibility with other versions of the data. As the system or application is upgraded, the data structure may change. Through the version number, the program that processes the data can adopt the corresponding parsing and processing methods. For example, when the data format is upgraded from version 1 to version 2, the program can judge and use the parsing logic corresponding to the new version based on the version number. The extension part provides flexibility and scalability for the data structure. Since its length is not limited, additional information can be added according to actual needs, such as metadata of specific applications, functional identifiers that may be needed in the future, etc. For example, as the business develops, it may be necessary to add information such as data encryption identifiers and data source identifiers, which can be placed in the extension part without modifying the fixed-length data part, ensuring the compatibility and maintainability of the data structure.

[0035] The length of the record value does not include the 1 byte it occupies. The maximum length of the record value is 255 bytes, and the record value data type is encoded in UTF8.

[0036] Table 2

[0037] Specifically, the specific format of the record area can be referred to in Table 3 below. The record value length of the record area is 1 byte specifically used to store the length information of the record value. Since 1 byte is equal to 8 bits, its value range is 0-255. It can represent the length of the record value, and this length value can help the system accurately know the size of the space occupied by the subsequent record value. The record value is the actual stored data content, and its length is not fixed. This variable length design enables the data structure to store data of various types and lengths.

[0038] Table 3

[0039] It should be noted that the area code and user number range is 0000-9999. If you want to parse the regional information based on the mobile phone number, you can parse it based on the first 7 digits of the mobile phone number, which ranges from 1300000 to 1999999. It takes 6 bytes (range 0-16777215) to store the first 7 digits of a mobile phone number. If you want to reduce the size of the data file, you can subtract 1300000 from the first 7 digits of the mobile phone number. In this way, 0-700000 entries require at least 5 bytes (range 0-1048575) for storage. You can use byte data types and int (occupying 4 bytes) data types for indexing.

[0040] Specifically, since the first 7 digits of the mobile phone number 1300000 occupy 5 bytes and cannot be used as a basic type, it is split into int data type (occupying 4 bytes) as a secondary index and byte data type as a primary index. The specific format of each secondary index in the secondary index is shown in Table 4 below. The index address is 4 bytes and is used to store an address value. Assuming that this structure can store a total of 700,000 numbers (mobile phone numbers), the number of secondary indexes can be calculated according to the following formula: 700000 >> 8 = 2734 + 1 + 1 = 2736 secondary indexes, and the value of the additional one is the total number of bytes in the file.

[0041] Table 4

[0042] For example, since the range of mobile phone numbers is fixed, the number of secondary indexes is also fixed. The first 7 digits of mobile phone numbers - 1300000 are 700000 in total, and the number of secondary indexes is 700000 / 256=2734.375. The last group of mobile phone numbers needs to be recorded, and the number of decimals needs to be rounded up, which is 2735. The end address of the last primary index also needs to be recorded, and the final number of entries is 2736. For example, the first and second entries record the first-level index addresses of mobile phone numbers with the first 7 digits of 1300000-1300255, and the storage results are shown in Table 5 below.

[0043] Table 5

[0044] Specifically, the specific format of each primary index in the primary index can be referred to in Table 6 below. This 1 byte is used to store "number" related information, specifically the first 7 digits of the mobile phone number 1300000. These 4 bytes are used to store the "record address". In a computer storage system, the address is used to locate the location of data in the storage medium. In a 32-bit system, 4 bytes can represent 2 32 different address values.

[0045] Table 6

[0046] For example, in the order of the first 7 digits of the mobile phone number, each first 7 digit of the mobile phone number records a primary index, where the first byte is the value of the first 7 digits of the mobile phone number - 1300000 modulo 256, and the following 4 bytes are the record address. For example, if the first 7 digits of the mobile phone number are 1875471, the storage result is shown in Table 7 below.

[0047] Table 7

[0048] Among them, based on the above storage structure, a specific pre-storage process is given: Referring to Table 8, the original data is recorded, and the format of each original record is "the first 7 digits of the mobile phone number, province, city, ISP" and separated by "|", such as "1875471|S Province|J City|Mobile", and each original record occupies one line. Read all the original data, and split each original record into the format of "the first 7 digits of the mobile phone number" and "province|city|ISP" (record), put the record into a deduplicated and sorted array, and put the first 7 digits of the mobile phone number and the record value feature code (hash value) into the array. Specify the record area address, traverse the record array, and put the feature code (hash value), address and record value of each record into the sequential mapping. Calculate the storage capacity occupied by the record area and the first-level index area, so as to determine the file size. Create a file, and put the data in the order of the record area, the first-level index area, the second-level index area, and the header area, wherein the header area puts the data in the order of the checksum, version number, record area address, second-level index area address, and first-level index area address. Optionally, compress the file, either in zip format or in other formats, which are not limited here.

[0049] Table 8

[0050] Specifically, in the generated uncompressed file, the header area address is 00000000-00000013, a total of 20 bytes, please refer to Table 9; the record area address is 00000014-0000ABAF, a total of 43932 bytes, please refer to Table 10, the record value length in brackets is the decimal length, and the record value in brackets is the UTF8 encoded value; the secondary index area address is 0000ABB0-0000D66F, a total of 10944 bytes, please refer to Table 11; the first-level index area address is 0000D670-0026C532, a total of 2485955 bytes, please refer to Table 12.

[0051] Table 9

[0052] Table 10

[0053] Table 11

[0054] Table 12

[0055] It should be noted that the above-mentioned expression of (letter) country (letter) province (letter) city, such as N Province X City, is only used for illustration. In actual use, the letter part is the specific actual region name.

[0056] It can be seen that in this embodiment, a mobile phone number database with a multi-level index structure as described above is proposed, and the storage format and corresponding storage data length and other storage flexibility and scalability, the specific storage split format and data type maximize the use of storage space, and the use of primary index and secondary index and the length limit of the index structure can improve the efficiency of index construction and perform efficient address mapping. In addition, the indexing speed can be accelerated, the storage space occupied can be reduced, and the efficiency of number resolution can be improved, and the system burden can be reduced.

[0057] In a possible embodiment, a multi-level indexing operation is performed based on the first number and the pre-built number database to obtain the first attribution information, including: performing a data conversion operation on the first number to obtain standard number information; determining address location information based on the standard number information; performing an indexing operation based on the address location information and a binary indexing operation to determine the first attribution information.

[0058] Before the first number is indexed in the pre-built number database, it is necessary to first intercept the first number to obtain the effective part for screening. Specifically, the first 7 digits of the phone number are used for the location determination, so the first 7 digits are intercepted. Then the effective part is adjusted to a structure consistent with the structure of the data stored in the database for retrieval, that is, standard number information; then the start location is performed in the pre-built number database based on the standard number information, that is, the starting position for the retrieval, that is, the address location information; then the address location information is indexed, and the binary index operation can be used during the indexing process, and the first location information is finally indexed.

[0059] Optionally, performing an indexing operation based on the address location information and a binary indexing operation, determining the first attribution information may include the following steps: determining a first-level index boundary value based on a first preset step size and the address location information, the first-level index boundary value including a first-level index left boundary value and a first-level index right boundary value; judging whether the boundary value meets a condition based on the first-level index boundary value, the condition being whether the first-level index left boundary value is unequal to the first-level index right boundary value; if they are equal, indexing cannot be performed, and the situation is reported, the search is terminated, and an empty attribution address is output; if they are unequal, indexing is performed based on a binary indexing operation to determine the first-level index address; if the first-level index address is empty, the situation is reported, the search is terminated; if the first-level index address is found, data is read based on a second preset step size to determine the record address value; repositioning the read pointer of the data file to the record address value; reading data of a third preset step size as a record length value; and reading a preset number of bytes from the current position to obtain the first attribution information.

[0060] The first preset step size may be 4 bytes, the second preset step size may be 4 bytes, the third preset step size may be 1 byte, and the number of preset bytes is not limited here. The specific values ​​of the first preset step size, the second preset step size, and the third preset step size are related to the specific structure of the pre-built number database.

[0061] Optionally, performing a data conversion operation on the first number to obtain standard number information includes: intercepting based on the first number to determine the second number, the number of characters contained in the second number is less than or equal to the number of characters contained in the first number; performing a numerical type conversion operation based on the second number to obtain the standard number information, the numerical type of the standard number information includes an integer type.

[0062] Among them, since the mobile phone number is 7-11 digits, the first 7 digits are associated with the place of origin, the intercepted second number can be obtained by intercepting the first 7 digits, and then the second number is converted into a numerical type to obtain standard number information. Specifically, the numerical type conversion process may include: subtracting 1300000, dividing by 256 and taking the integer part, and then multiplying by 4. Specifically, the intercepted first 7 digits are subtracted and 1300000 is subtracted. This step is to map the first 7 digits of the mobile phone number to a range that is easier to process and index. The difference obtained in the previous step is divided by 256 and the integer part is taken, which is to locate the specific index item in the secondary index. Because the secondary index is constructed based on every 256 numerical ranges according to certain rules, through this step, the approximate position of the first 7 digits of the input mobile phone number in the secondary index can be determined. The integer result obtained in the previous step is multiplied by 4, because in the secondary index area, each index item occupies 4 bytes. By multiplying by 4, the offset in the secondary index area can be obtained so as to accurately find the corresponding secondary index item. Through this step, the information can be simplified to key information, which is more suitable for indexing, and the value mapping process is optimized to improve indexing efficiency.

[0063] Optionally, determining the address location information based on the standard number information includes: performing an address association operation on the standard number information to determine starting position information of the index, wherein the starting position information is an address in the secondary index area.

[0064] The address association operation is to combine the standard number information with the starting address of the secondary index area, specifically, to determine the starting position information of the index, that is, to start indexing from here.

[0065] It can be seen that through the above indexing process, the starting position can be efficiently located based on the processed mobile phone numbers. The processing of mobile phone numbers can improve the inclusiveness of mobile phone numbers, increase the correlation between mobile phone numbers and indexes, and thus improve the efficiency of indexing.

[0066] It can be seen that through the specific structure of the above-mentioned pre-built number database and the parsing method based on the pre-built number database, 700,000 mobile phone number locations can be stored in only more than 800KB of memory, and the average time required to parse a mobile phone number location is 2.47 microseconds; combined with the storage structure to store and parse mobile phone numbers and mobile phone number location information and usage records to generate user portraits, the push of energy information can be more accurate and efficient, saving storage.

[0067] S230, performing feature analysis based on the user information to determine user features, the user features including second attribution information and / or intention feature information, the second attribution information is used to characterize the current location information of the user of the first number, and the intention feature information is used to characterize the user's preference for push information.

[0068] The second attribution information is different from the first attribution information. The first attribution information is the fixed attribution location corresponding to the first number, and the second attribution information is variable, which is the area information where the user of the first number is currently located. The intention feature information is used to characterize the user's preference for push information, which can be obtained by analyzing the user's viewing of the information, such as clicks, viewing time, search content, etc., that is, the content included in the user information.

[0069] In a possible embodiment, the operation information includes selection information and / or information browsing time and / or input text information and / or feedback information, and the feedback information is preference feedback information actively selected by the user. The feature analysis based on the user information to determine the user characteristics includes: determining information intention parameters based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or input text information and a preset first influencing factor set; determining the intention feature information by sorting based on the information intention parameters; and determining the second attribution information by performing a feature extraction operation based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or input text information.

[0070] The first set of influencing factors may be preset, including multiple influencing factors for various types of information, and the weight of each factor may be determined by expert evaluation, historical data statistical analysis, or machine learning algorithms (such as analytic hierarchy process, regression analysis, etc.). For example, if it is found through analysis that users pay more attention to newly released content, the weight of the information release time factor may be set relatively high.

[0071] Among them, aggregation and preprocessing are performed based on one or more of the selection information, the information browsing time for the selection information, the feedback information for the selection information, and the input text information. Specifically, the same type of data can be aggregated and counted, and it can also include processes such as data standardization, which are not limited here.

[0072] Among them, feature extraction is performed from the selection information, the information browsing time for the selection information, the feedback information for the selection information, and the input text information. Specifically, it can be text feature extraction to extract information related to the region, and the second attribution information is determined based on the information related to the region.

[0073] For example, the system records the types of energy data that users actively choose to view on the energy data platform, such as electricity data, natural gas data, coal data, solar energy data, etc. And record the browsing time of the corresponding data types. Collect feedback information left by users for each type of energy data, including but not limited to scoring (1-5 points), likes, sharing, marking dislikes and other operations. If the platform is equipped with a user input box, collect text information related to energy data actively input by users, such as comments or searches. Feature extraction or center analysis of the above data is performed to obtain relevant data around multiple types of data. For example, for a certain type of energy information M, the browsing time is A, the number of selections is B, the feedback information for the selected information is quantified as C, and the input text information is processed and quantified as D. The first impact factor set includes a for browsing time, b for the number of selections, c for the selected information, and d for the input text. Then the information intention parameter for M is: M=aA+bB+cC+dD. Then, all types of energy information are analyzed for information intention parameters, which can be sorted and summarized. After sorting from high to low, information intention parameters in a certain range are determined as intention feature information, which is used to constrain the number of pushes for each type of energy information.

[0074] It can be seen that in this embodiment, the data information generated by the first number that can be obtained by various energy management platforms is analyzed and summarized, specifically including the regional information, which can make the push information more accurate and more targeted.

[0075] In a possible embodiment, the energy management system also includes multiple energy sub-platforms, and the user information includes a first type of user information and / or a second type of user information, the first type of user information is the operation information, and the second type of user information includes data information from multiple energy sub-platforms associated with the energy management platform; the information intention parameters determined based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and a preset multiple influencing factors include: determining the energy demand information of the user of the first number based on the second type of user information, the energy demand including the energy demand or energy consumption demand for new energy vehicles; determining the information intention parameters based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and / or the energy demand information and a preset second influencing factor set.

[0076] Among them, the first type of user information is the content described in other embodiments above, including selection information and / or information browsing time and / or input text information and / or feedback information, etc.; the second type of user information is data information of other related multiple energy sub-platforms. Other related multiple energy sub-platforms can be new energy charging pile platforms, electricity payment platforms, and other related energy management platforms, which may include but are not limited to wind energy, thermal energy, etc., which are not specifically limited here. Energy demand information is the energy actually used by the user of the first number, for example, when using new energy charging piles, paying household electricity bills, paying corporate factory electricity bills, etc.

[0077] Among them, the second influencing factor set can be preset, including multiple influencing factors for various types of information, and the weight of each factor can be determined through expert evaluation, historical data statistical analysis or machine learning algorithm (such as hierarchical analysis method, regression analysis, etc.).

[0078] Specifically, the specific operation process is similar to the previous implementation process, adding the influencing factor of the energy demand information and considering the actual demand for pushing. The specific process is the same as the previous embodiment process, adding the calculation content of the energy demand information, which will not be repeated here, please refer to the above embodiment process.

[0079] It can be seen that in this embodiment, the data information generated by the first number that can be obtained by various energy management platforms is analyzed and summarized, specifically including the first attribution information and the second attribution information, and accurate push of energy data related to the region is performed based on the first attribution information and the second attribution information, which can make the pushed information more accurate and more targeted.

[0080] S240: Determine push content for the first number based on the first attribution information and / or the second attribution information and / or the intention feature information, and push information based on the push content.

[0081] Among them, when the user is using it for the first time, or deletes the usage record of the historical time period in some way, such as logging out, there may be only the first attribution information, and the second attribution information is empty. Furthermore, the user information is empty, that is, the intention feature information is also empty. The push content can be determined only based on the first attribution information. It should be noted that the push content is not entirely targeted at the first attribution information, and part or all of the content may be targeted at the first attribution information.

[0082] Wherein, if the user information is not empty, the first attribution information and the second attribution information can be extracted, and the push content is determined based on the first attribution information, the second attribution information and the intention characteristic information. In some possible cases, the push content is determined only based on the second attribution information and the intention characteristic information; in some possible cases, the push content is determined only based on the intention characteristic information.

[0083] Specifically, the method of weight assignment may be selected to analyze the pushed content based on multiple factors, or other methods may be used, which are not limited here.

[0084] In a possible embodiment, the determining of the push content of the first number based on the first attribution information and / or the second attribution information and / or the intention characteristic information includes: determining a regional importance coefficient based on the first attribution information, the second attribution information and the user characteristics, the regional importance coefficient being used to constrain the push content proportion coefficient for the first attribution information and the second attribution information; determining the push content with regional characteristics based on the importance coefficient, the first attribution information, the second attribution information and the intention characteristic.

[0085] Among them, the regional importance coefficient can be determined from the proportion of each type of attribution information in the user characteristics. For example, the regional importance coefficient of the first attribution is 54, the second attribution is 22, and the sum of the two is 76. Then the push content proportion coefficient of the first attribution information = 54 / 76≈71%, and the push content proportion coefficient of the second attribution information = 22 / 76≈29%. Then, based on the proportion coefficient, push content for the different proportions of the first attribution information and the second attribution information, and push content based on this.

[0086] In some possible cases, a correction factor may be determined for the content proportion coefficient, and the correction factor is used to limit the proportion to avoid extremely extreme situations, such as 0% and 100%.

[0087] For example, the first proportion coefficient is P, the second proportion coefficient is Q, the first correction coefficient is p, and the second correction coefficient is q, then the final proportions are Pp and Qq.

[0088] It can be seen that in this embodiment, by performing a proportion analysis, the relevance and practicality of the pushed content are greatly improved, which helps to improve user stickiness. At the same time, it also accumulates richer user data for the platform, optimizes the pushed content considering the actual situation and the first attribution information and the second attribution information, and improves the accuracy of pushing energy information preferences.

[0089] It can be seen that by implementing the embodiment of the present application, the first number and the user information corresponding to the first number are obtained, the first number is the number that triggers the refresh operation of the push content of the energy management platform, the first number has a binding relationship with the energy management platform, and the user information includes the operation information of the user of the first number for the energy information of the energy management platform in the historical time period; based on the first number and the pre-built number database, a multi-level index operation is performed to obtain the first attribution information, and the first attribution information is the regional information of the first number; based on the user information, a feature analysis is performed to determine the user characteristics, and the user characteristics include the second attribution information and / or the intention feature information, the second attribution information is used to characterize the current location information of the user of the first number, and the intention feature information is used to characterize the user's preference for the push information; based on the first attribution information and / or the second attribution information and / or the intention feature information, the push content of the first number is determined, and information is pushed based on the push content. In this way, by combining the first attribution information and the second attribution information and the intention, the push accuracy of the energy information preference can be improved, and by constructing a number database with a multi-level index, the number resolution efficiency can be improved, and the occupied space can be reduced, thereby improving the efficiency of preference analysis and reducing the system burden.

[0090] See also Figure 4 , Figure 4This is a functional unit composition block diagram of an intelligent push device proposed in an embodiment of the present application. The device is applied to a server of an energy management system. The energy management system also includes an energy management platform and a first memory. The first memory is provided with a pre-built number database. The pre-built number database includes a multi-level index structure. The intelligent push device 400 includes: an acquisition module 410, which is used to acquire a first number and user information corresponding to the first number, wherein the first number is a number that triggers a refresh operation on the push content of the energy management platform, and the first number has a binding relationship with the energy management platform, and the user information includes operation information of the user of the first number on the energy information of the energy management platform within a historical time period; an index module 420, which is used to perform a multi-level indexing operation based on the first number and the pre-built number database to obtain first attribution information, wherein the first attribution information is the regional information of the first number; a feature determination module 430, which is used to perform feature analysis based on the user information to determine user features, wherein the user features include second attribution information and / or intention feature information, wherein the second attribution information is used to characterize the current location information of the user of the first number, and the intention feature information is used to characterize the user's preference for push information; a content determination module 440, which is used to determine the push content of the first number based on the first attribution information and / or the second attribution information and / or the intention feature information, and push information based on the push content.

[0091] In a possible embodiment, the multi-level index structure of the pre-constructed number database includes a primary index area and a secondary index area, and the pre-constructed address database includes a header area, a record area, the secondary index area and the primary index area; the addresses of the header area, the record area, the secondary index area and the primary index area have an address association relationship, and the address association relationship includes a sequential continuation relationship; the record area is used to store resolution information data, the resolution information data represents at least one level of attribution region and operator information, and the resolution information data is variable-length data.

[0092] In a possible embodiment, the index module 420, in performing a multi-level indexing operation based on the first number and the pre-built number database to obtain the first attribution information, is specifically configured to: Performing a data conversion operation on the first number to obtain standard number information; Determining address location information based on the standard number information; An indexing operation is performed based on the address location information and a binary indexing operation to determine the first attribution information.

[0093] In a possible embodiment, the index module 420, in performing a data conversion operation on the first number to obtain standard number information, is specifically configured to: Determine a second number by intercepting the first number, wherein the number of characters included in the second number is less than or equal to the number of characters included in the first number; Performing a numerical type conversion operation based on the second number to obtain the standard number information, where the numerical type of the standard number information includes an integer type; The determining of the address location information based on the standard number information comprises: The standard number information is subjected to an address association operation to determine the starting position information of the index, where the starting position information is the address in the secondary index area.

[0094] In a possible embodiment, the operation information includes selection information and / or information browsing time and / or input text information and / or feedback information. The feature determination module 430 regards the feedback information as the preference feedback information actively selected by the user, and performs feature analysis based on the user information to determine the user feature, specifically for: Determine the information intention parameter based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and a preset first influencing factor set; Determine the intention characteristic information by sorting based on the information intention parameters; The second attribution information is determined by performing a feature extraction operation based on the selection information and / or the information browsing duration for the selection information and / or the feedback information for the selection information and / or the input text information.

[0095] In a possible embodiment, the energy management system further includes multiple energy sub-platforms, the user information includes first-category user information and / or second-category user information, the first-category user information is the operation information, and the second-category user information includes data information from multiple energy sub-platforms associated with the energy management platform; the feature determination module 430 is specifically used to determine the information intention parameter based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and the preset multiple influencing factors: Determine energy demand information of the user of the first number based on the second type of user information, where the energy demand includes energy demand or energy consumption demand for new energy vehicles; The information intention parameter is determined based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and / or the energy demand information and a preset second influencing factor set.

[0096] In a possible embodiment, the content determination module 440 is specifically configured to: Determine a regional importance coefficient based on the first attribution information, the second attribution information and the user characteristics, wherein the regional importance coefficient is used to constrain a push content proportion coefficient for the first attribution information and the second attribution information; Push content with regional characteristics is determined based on the importance coefficient, the first attribution information, the second attribution information, and the intention characteristics.

[0097] It is worth noting that the specific functional implementation of the intelligent push device 400 is shown in the above Figure 2 The description of the intelligent push method shown, such as the acquisition module is used to implement the relevant content of executing S210. The various units or modules in the intelligent push device 400 can be individually or completely combined into one or several other units or modules to constitute, or one (some) of the units or modules can be further divided into multiple functionally smaller units or modules to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present invention. The above-mentioned units or modules are divided based on logical functions. In actual applications, the functions of one unit (or module) are implemented by multiple units (or modules), or the functions of multiple units (or modules) are implemented by one unit (or module).

[0098] In the case of integrated units, see Figure 5 , Figure 5 is a block diagram of the functional units of another intelligent push device proposed in an embodiment of the present application, such as Figure 5 As shown, the intelligent push device 400 includes: a communication module 401 and a processing module 402. The processing module 402 is used to control and manage the actions of the intelligent push device 400, for example, the steps of the acquisition module 410, the index module 420, the feature determination module 430 and the content determination module 440 and / or other processes for executing the technology described herein. The communication module 401 is used for the interaction between the intelligent push device 400 and other devices, such as an energy management platform or a terminal device. Figure 5 As shown, the smart push device 400 may further include a storage module 403 , and the storage module 403 is used for program codes and data of the smart push device 400 .

[0099] Among them, the processing module 402 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic boxes, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 401 can be a transceiver, an RF circuit or a communication interface, and the like.

[0100] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0101] See also Figure 6 , Figure 6 is a schematic diagram of the structure of an electronic device proposed in an embodiment of the present application, such as Figure 6 As shown, the electronic device 600 includes a processor 610 , a second memory 620 , a communication interface 630 , and one or more programs 621 . The one or more programs 621 are stored in the second memory 620 and are configured to be executed by the processor 610 .

[0102] The processor 610, the second memory 620, and the communication interface 630 are connected to each other and perform communication work with each other.

[0103] The second memory 620 may be a volatile memory such as a dynamic random access memory DRAM, or a non-volatile memory such as a mechanical hard disk. The second memory 620 is used to store a set of executable program codes, and the processor 610 is used to call one or more programs 621 stored in the second memory 620, and may execute some or all steps of any smart push method recorded in the above-mentioned smart push method embodiment.

[0104] Among them, the electronic device 600 may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, driving recorders, vehicle-mounted electronic devices, servers, laptops, mobile Internet electronic devices (MID, Mobile Internet Devices) or wearable electronic devices (such as smart watches, Bluetooth headsets), etc. The above are only examples and not exhaustive, including but not limited to the above electronic devices.

[0105] It should be noted that the first memory and the second memory may be the same memory or different memories.

[0106] It can be seen that the electronic device 600 obtains the first number and the user information corresponding to the first number, the first number is the number that triggers the refresh operation of the push content of the energy management platform, the first number has a binding relationship with the energy management platform, and the user information includes the operation information of the user of the first number on the energy information of the energy management platform in the historical time period; based on the first number and the pre-built number database, a multi-level index operation is performed to obtain the first attribution information, the first attribution information is the regional information of the first number; based on the user information, a feature analysis is performed to determine the user characteristics, the user characteristics include the second attribution information and / or the intention feature information, the second attribution information is used to characterize the current location information of the user of the first number, and the intention feature information is used to characterize the user's preference intention for the push information; based on the first attribution information and / or the second attribution information and / or the intention feature information, the push content of the first number is determined, and information is pushed based on the push content. In this way, the push accuracy of energy information preference can be improved by combining the first attribution information and the second attribution information and the intention, and the number resolution efficiency can be improved by constructing a number database with a multi-level index, and the occupied space can be reduced, thereby improving the efficiency of preference analysis and reducing the system burden.

[0107] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0108] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0109] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0110] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0111] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0112] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0114] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer electronic device (which can be a personal computer, electronic device or network electronic device, etc.) to perform all or part of the steps of the above-mentioned methods in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0115] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0116] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An intelligent push method, characterized in that: A server applied to an energy management system, the energy management system further comprising an energy management platform and a first memory, the first memory being provided with a pre-built number database, the pre-built number database comprising a multi-level index structure, the method comprising: Obtaining a first number and user information corresponding to the first number, wherein the first number is a number for triggering a refresh operation on content pushed by the energy management platform, the first number is bound to the energy management platform, and the user information includes operation information of the user of the first number on energy information of the energy management platform within a historical time period; Performing a multi-level indexing operation based on the first number and the pre-built number database to obtain first attribution information, where the first attribution information is the region information of the first number; Performing feature analysis based on the user information to determine user features, the user features including second attribution information and / or intention feature information, the second attribution information is used to represent the current location information of the user of the first number, and the intention feature information is used to represent the user's preference for push information; The push content of the first number is determined based on the first attribution information and / or the second attribution information and / or the intention characteristic information, and information is pushed based on the push content.

2. The method according to claim 1, characterized in that The multi-level index structure of the pre-constructed number database includes a primary index area and a secondary index area, and the pre-constructed address database includes a header area, a record area, the secondary index area and the primary index area; the addresses of the header area, the record area, the secondary index area and the primary index area have an address association relationship, and the address association relationship includes a sequential continuation relationship; the record area is used to store resolution information data, the resolution information data represents at least one level of belonging area and operator information, and the resolution information data is variable-length data.

3. The method according to claim 2, characterized in that The performing a multi-level indexing operation based on the first number and the pre-built number database to obtain the first attribution information includes: Performing a data conversion operation on the first number to obtain standard number information; Determining address location information based on the standard number information; An indexing operation is performed based on the address location information and a binary indexing operation to determine the first attribution information.

4. The method according to claim 3, characterized in that The performing of data conversion operation on the first number to obtain standard number information includes: Determine a second number by intercepting the first number, wherein the number of characters included in the second number is less than or equal to the number of characters included in the first number; Performing a numerical type conversion operation based on the second number to obtain the standard number information, where the numerical type of the standard number information includes an integer type; The determining of the address location information based on the standard number information includes: The standard number information is subjected to an address association operation to determine the starting position information of the index, where the starting position information is the address in the secondary index area.

5. The method according to claim 1, characterized in that The operation information includes selection information and / or information browsing time and / or input text information and / or feedback information, and the feedback information is the preference feedback information actively selected by the user. The feature analysis based on the user information to determine the user features includes: Determine the information intention parameter based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and a preset first influencing factor set; Determine the intention characteristic information by sorting based on the information intention parameters; The second attribution information is determined by performing a feature extraction operation based on the selection information and / or the information browsing duration for the selection information and / or the feedback information for the selection information and / or the input text information.

6. The method according to claim 5, characterized in that The energy management system further includes a plurality of energy sub-platforms, the user information includes first-category user information and / or second-category user information, the first-category user information is the operation information, and the second-category user information includes data information from a plurality of energy sub-platforms associated with the energy management platform; the information intention parameter determined based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and the preset plurality of influencing factors includes: Determine energy demand information of the user of the first number based on the second type of user information, where the energy demand includes energy demand or energy consumption demand for new energy vehicles; The information intention parameter is determined based on the selection information and / or the information browsing time for the selection information and / or the feedback information for the selection information and / or the input text information and / or the energy demand information and a preset second influencing factor set.

7. The method according to claim 1, characterized in that The determining the push content of the first number based on the first attribution information and / or the second attribution information and / or the intention feature information includes: Determine a regional importance coefficient based on the first attribution information, the second attribution information and the user characteristics, wherein the regional importance coefficient is used to constrain a push content proportion coefficient for the first attribution information and the second attribution information; Push content with regional characteristics is determined based on the importance coefficient, the first attribution information, the second attribution information, and the intention characteristics.

8. An intelligent push device, characterized in that: A server applied to an energy management system, the energy management system further comprising an energy management platform and a first memory, the first memory being provided with a pre-built number database, the pre-built number database comprising a multi-level index structure, the device comprising: an acquisition module, configured to acquire a first number and user information corresponding to the first number, wherein the first number is a number for triggering a refresh operation on content pushed by the energy management platform, the first number is bound to the energy management platform, and the user information includes operation information of the user of the first number on energy information of the energy management platform within a historical time period; An indexing module, configured to perform a multi-level indexing operation based on the first number and the pre-built number database to obtain first attribution information, wherein the first attribution information is the region information of the first number; a feature determination module, configured to determine user features by performing feature analysis based on the user information, wherein the user features include second attribution information and / or intention feature information, wherein the second attribution information is used to represent the current location information of the user of the first number, and the intention feature information is used to represent the user's preference for push information; The content determination module is used to determine the push content of the first number based on the first attribution information and / or the second attribution information and / or the intention characteristic information, and push information based on the push content.

9. A computer-readable storage medium, characterized in that: An intelligent push program is stored, including execution instructions. When a processor of an electronic device executes the execution instructions, the processor executes the method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: It comprises a processor and a second memory storing execution instructions, wherein the second memory stores one or more programs; when the processor executes the execution instructions stored in the second memory, the processor executes the method as claimed in any one of claims 1 to 7.

Images